HIROKI TAKAHASHI
| Department of Informatics | Professor |
| Cluster I (Informatics and Computer Engineering) | Professor |
| Meta-Networking Research Center | Professor |
| Artificial Intelligence eXploration Research Center | Professor |
Researcher Information
Field Of Study
Career
- 01 Apr. 2022
the University of Electro-Communication, Graduate School of Informatics and Engineering, Department of Informatics, Professor - 01 Apr. 2016 - 31 Mar. 2022
the University of Electro-Communication, Graduate School of Informatics and Engineering, Department of Informatics, Associate Professor - 01 Apr. 2010 - 31 Mar. 2016
the University of Electro-Communication, Graduate School of Informatics and Engineering, Department of Informatics, Associate Professor - 01 Apr. 2007 - 31 Mar. 2010
Department of Human Communication, the University of Electro-Communications, Associate Professor - 01 Apr. 2006 - 31 Mar. 2007
Department of Human Communication, the University of Electro-Communications, Associate Professor - 01 Jul. 1994 - 31 Mar. 2006
Department of Computer Science, Graduate School of Information Science & Engineering, Tokyo Institute of Technology, Assistant Professor - 01 Apr. 1994 - 30 Jun. 1994
Department of Computer Science, School of Engineering, Tokyo Institute of Technology, Research Associate
Educational Background
Research Activity Information
Award
- Jan. 2024
International Workshop on Advanced Imaging Technology (IWAIT) 2024
YEEHaD: YOLO-based Extremely Efficient Hand Detection for Embedded Systems
Best Paper Award, Gibran Benitez-Garcia;Hiroki Takahashi - Aug. 2023
The 24th International Conference on Parallel and Distributed Computing, Applications and Technologies(PDCAT2023)
SAHF-LightPoseResNet: Spatially-aware Attentionbased Hierarchical Features Enabled Lightweight PoseResNet for 2D Human Pose Estimation
Best Paper Award, Ali Zakir;Sartaj Ahmed Salman;Hiroki Takahashi - Sep. 2022
画像電子学会
マルチモーダル学習を用いたリビングルーム画像のパーソナライズド感性検索
優秀論文賞, 小林 菜穂子;高橋 裕樹
Official journal - Jan. 2022
International Workshop on Advanced Imaging Technology (IWAIT) 2022
Comparison of Real-time CNN-based Methods for Finger-Level Hand Segmentation
Best Paper Award, Gibran Benitez-Garcia;Natsuki Takayama;Jesus Olivares-Mercado;Gabriel Sanchez-Perez;Hiroki Takahashi - Nov. 2017
芸術科学会
貢献賞
Japan society - Mar. 2016
映像情報表現・芸術科学フォーラム2016
キメ分析に基づく肌状態変化計測
口頭発表優秀賞
Japan society - Mar. 2008
芸術科学会
CGアニメーションカンファレンスNICOGRAPH Spring Festival in TAF, 優秀ポスター賞 - Mar. 2008
芸術科学会
芸術科学会，CG国際大賞優秀論文賞 - Jun. 2006
Shape Modeling and Applications 2006
Shape Modeling and Applications 2006, Best Paper Award - Dec. 2004
the 5th International Conference on Intelligent Technologies(InTech'04)
the 5th International Conference on Intelligent Technologies(InTech'04), Best Research Paper Award - Nov. 2003
NICOGRAPH
第19回 NICOGRAPH論文コンテスト 最優秀論文賞 - Apr. 2003
映像メディア学会誌
映像メディア学会誌 ベストオーサ賞 - Oct. 2002
NICOGRAPH
第18回 NICOGRAPH 論文コンテスト審査員特別賞 - May 2002
NICOGRAPH International
NICOGRAPH International 2002 Best Paper Award - 2001
電子情報通信学会
電子情報通信学会 学術奨励賞
Paper
- Efficient 3Dconv Fusion of RGB and Optical Flow for Dynamic Hand Gesture Recognition and Localization
Gibran Benitez-Garcia; Hiroki Takahashi
Last, 11th Pacific-Rim Symposium on Image and Video Technology (PSIVT 2023), Springer Nature Singapore, 197-210, 12 Feb. 2024, Peer-reviwed
International conference proceedings, English - Generative approaches for solving tangram puzzles
Fernanda Miyuki Yamada; Harlen Costa Batagelo; João Paulo Gois; Hiroki Takahashi
Last, Discover Artificial Intelligence, Springer Science and Business Media LLC, 4, 1, 08 Feb. 2024, Peer-reviwed, Abstract
The Tangram is a dissection puzzle composed of seven polygonal pieces that can form different patterns. Solving the Tangram is an irregular shape packing problem known to be NP-hard. This paper investigates the application of four deep-learning architectures—Convolutional Autoencoder, Variational Autoencoder, U-Net, and Generative Adversarial Network—specifically designed for solving Tangram puzzles. We explore the potential of these architectures in learning the complex spatial relationships inherent in Tangram configurations. Our experiments show that the Generative Adversarial Network competes well with other architectures and converges considerably faster. We further prove that traditional evaluation metrics based on pixel accuracy often fail in assessing the visual quality of the generated Tangram solutions. We introduce a loss function based on a Weighted Mean Absolute Error that prioritizes pixels representing inter-piece sections over those covered by individual pieces. Extending this loss function, we propose a novel evaluation metric as a more fitting measure for assessing Tangram solutions compared to traditional metrics. This investigation advances our understanding of the capabilities of artificial intelligence in complex geometrical problem domains.
Scientific journal, English - FingerSeg: Highly-Efficient Dual-Resolution Architecture for Precise Finger-Level Semantic Segmentation
Gibran Benitez-Garcia; Hiroki Takahashi
Last, Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, SCITEPRESS - Science and Technology Publications, 3, 242-251, Feb. 2024, Peer-reviwed
International conference proceedings, English - Deformable Pose Network: A Multi-Stage Deformable Convolutional Network for 2D Hand Pose Estimation
Sartaj Salman; Ali Zakir; Hiroki Takahashi
Last, Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, SCITEPRESS - Science and Technology Publications, 3, 814-821, Feb. 2024, Peer-reviwed
International conference proceedings, English - EBA-PRNetCC: An Efficient Bridge Attention-Integration PoseResNet for Coordinate Classification in 2D Human Pose Estimation
Ali Zakir; Sartaj Salman; Gibran Benitez-Garcia; Hiroki Takahashi
Last, Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, SCITEPRESS - Science and Technology Publications, 3, 133-144, Feb. 2024, Peer-reviwed
International conference proceedings, English - SOCA-PRNet: Spatially Oriented Attention-Infused Structured-Feature-Enabled PoseResNet for 2D Human Pose Estimation
Ali Zakir; Sartaj Ahmed Salman; Hiroki Takahashi
Last, Sensors, MDPI AG, 24, 1, 110-110, 25 Dec. 2023, Peer-reviwed, In the recent era, 2D human pose estimation (HPE) has become an integral part of advanced computer vision (CV) applications, particularly in understanding human behaviors. Despite challenges such as occlusion, unfavorable lighting, and motion blur, advancements in deep learning have significantly enhanced the performance of 2D HPE by enabling automatic feature learning from data and improving model generalization. Given the crucial role of 2D HPE in accurately identifying and classifying human body joints, optimization is imperative. In response, we introduce the Spatially Oriented Attention-Infused Structured-Feature-enabled PoseResNet (SOCA-PRNet) for enhanced 2D HPE. This model incorporates a novel element, Spatially Oriented Attention (SOCA), designed to enhance accuracy without significantly increasing the parameter count. Leveraging the strength of ResNet34 and integrating Global Context Blocks (GCBs), SOCA-PRNet precisely captures detailed human poses. Empirical evaluations demonstrate that our model outperforms existing state-of-the-art approaches, achieving a Percentage of Correct Keypoints at 0.5 (PCKh@0.5) of 90.877 at a 50% threshold and a Mean Precision (Mean@0.1) score of 41.137. These results underscore the potential of SOCA-PRNet in real-world applications such as robotics, gaming, and human–computer interaction, where precise and efficient 2D HPE is paramount.
Scientific journal, English - ACENet: Attention-Driven Contextual Features-Enhanced Lightweight EfficientNet for 2D Hand Pose Estimation
Sartaj Ahmed Salman; Ali Zakir; Gibran Benitez-Garcia; Hiroki Takahashi
Last, 2023 38th International Conference on Image and Vision Computing New Zealand (IVCNZ), IEEE, 29 Nov. 2023, Peer-reviwed
International conference proceedings, English - AECA-PRNetCC: Adaptive Efficient Channel Attention-based PoseResNet for Coordinate Classification in 2D Human Pose
Ali Zakir; Sartaj Ahmed Salman; Gibran Benitez-Garcia; Hiroki Takahashi
Last, 2023 38th International Conference on Image and Vision Computing New Zealand (IVCNZ), IEEE, 29 Nov. 2023, Peer-reviwed
International conference proceedings, English - SDFPoseGraphNet: Spatial Deep Feature Pose Graph Network for 2D Hand Pose Estimation
Sartaj Ahmed Salman; Ali Zakir; Hiroki Takahashi
Last, Sensors, MDPI AG, 23, 22, 9088-9088, 10 Nov. 2023, Peer-reviwed, In the field of computer vision, hand pose estimation (HPE) has attracted significant attention from researchers, especially in the fields of human–computer interaction (HCI) and virtual reality (VR). Despite advancements in 2D HPE, challenges persist due to hand dynamics and occlusions. Accurate extraction of hand features, such as edges, textures, and unique patterns, is crucial for enhancing HPE. To address these challenges, we propose SDFPoseGraphNet, a novel framework that combines the strengths of the VGG-19 architecture with spatial attention (SA), enabling a more refined extraction of deep feature maps from hand images. By incorporating the Pose Graph Model (PGM), the network adaptively processes these feature maps to provide tailored pose estimations. First Inference Module (FIM) potentials, alongside adaptively learned parameters, contribute to the PGM’s final pose estimation. The SDFPoseGraphNet, with its end-to-end trainable design, optimizes across all components, ensuring enhanced precision in hand pose estimation. Our proposed model outperforms existing state-of-the-art methods, achieving an average precision of 7.49% against the Convolution Pose Machine (CPM) and 3.84% in comparison to the Adaptive Graphical Model Network (AGMN).
Scientific journal, English - Mixed 2D/3D YOLOv5 Backbone for Efficient Spatio-Temporal Hand Gesture Localization and Recognition
Luis Acevedo-Bringas; Gibran Benitez-Garcia; Jesus Olivares-Mercado; Hiroki Takahashi
Last, The 5th ASEAN UEC Workshop, Sep. 2023, Peer-reviwed
Research society, English - SAHF-LightPoseResNet: Spatially-aware Attentionbased Hierarchical Features Enabled Lightweight PoseResNet for 2D Human Pose Estimation
Ali Zakir; Sartaj Ahmed Salman; Hiroki Takahashi
Corresponding, The 24th International Conference on Parallel and Distributed Computing, Applications and Technologies(PDCAT2023), 43-54, Aug. 2023, Peer-reviwed
International conference proceedings, English - Diabetic Retinopathy Grading based on a Sparse Network Fusion of Heterogeneous ConvNeXt Models with Category Attention
Agustin Castillo-Munguia; Gibran Benitez-Garcia; Jesus Olivares-Mercado; Hiroki Takahashi
2023 18th International Conference on Machine Vision and Applications (MVA), IEEE, 23 Jul. 2023, Peer-reviwed
International conference proceedings, English - YOLOv5 with Mixed Backbone for Efficient Spatio-Temporal Hand Gesture Localization and Recognition
Luis Acevedo-Bringas; Gibran Benitez-Garcia; Jesus Olivares-Mercado; Hiroki Takahashi
Corresponding, 2023 18th International Conference on Machine Vision and Applications (MVA), IEEE, 23 Jul. 2023, Peer-reviwed
International conference proceedings, English - Cascaded deep graphical convolutional neural network for 2D hand pose estimation
Sartaj Ahmed Salman; Ali Zakir; Hiroki Takahashi
International Workshop on Advanced Imaging Technology (IWAIT) 2023, SPIE, 26 Mar. 2023, Peer-reviwed
International conference proceedings - TFM a Dataset for Detection and Recognition of Masked Faces in the Wild
Gibran Benitez-Garcia; Hiroki Takahashi; Miguel Jimenez-Martinez; Jesus Olivares-Mercado
Proceedings of the 4th ACM International Conference on Multimedia in Asia, ACM, 13 Dec. 2022
International conference proceedings, English - Twitter Face Image Mining for Recognition of Different Face Mask Types
Ulies Arroyo-Rojas; Miguel Jimenez-Martinez; Gibran Benitez-Garcia; Jesus Olivares-Mercado; Hiroki Takahashi
New Trends in Intelligent Software Methodologies, Tools and Techniques (SoMeT), 355, 298-309, Sep. 2022, Peer-reviwed
International conference proceedings, English - Comparison of Real-time CNN-based Methods for Finger-Level Hand Segmentation
Gibran Benitez-Garcia; Natsuki Takayama; Jesus Olivares-Mercado; Gabriel Sanchez-Perez; Hiroki Takahashi
Proc. SPIE 12177, International Workshop on Advanced Imaging Technology (IWAIT) 2022, 121770P, 1-6, 30 Apr. 2022, Peer-reviwed
International conference proceedings, English - Skeleton-based Online Sign Language Recognition using Monotonic Attention
Natsuki Takayama; Gibran Benitez-Garcia; Hiroki Takahashi
the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, 5, 601-608, Feb. 2022, Peer-reviwed
International conference proceedings, English - Masked Batch Normalization to Improve Tracking-Based Sign Language Recognition Using Graph Convolutional Networks
Natsuki Takayama; Gibran Benitez-Garcia; Hiroki Takahashi
16th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2021), 1-5, Dec. 2021, Peer-reviwed
International conference proceedings, English - Sign Language Recognition Based on Spatial-Temporal Graph Convolution -Transformer
Natsuki Takayama; Benitez-Garcia Gibran; Hiroki Takahashi
Journal of the Japan Society of Precision Engineering, Japan Society for Precision Engineering, 87, 12, 1028-1035, Dec. 2021, Peer-reviwed
Scientific journal, English - Personalized Kansei Retrieval of Living Room Images by Multimodal Learning
Naoko Kobayashi; Hiroki Takahashi
The Journal of the Institute of Image Electronics Engineers of Japan, 50, 4, 541-549, Oct. 2021, Peer-reviwed
Scientific journal, Japanese - “Utopia”: an Interactive Visual Experience --- Equal and Borderless World, from a Semantic Concept of a Painting to a Comprehensive Eye-Guidance ---
Negar Kaghazchi; Yuto Kobayashi; Hiroki Takahashi; Sachiko Kodama
The Journal of the Society for Art and Science, 20, 3, 183-193, 30 Sep. 2021, Peer-reviwed
Scientific journal, English - Raster-Based Mathematical Morphology for Cutting and Packing Problems
Fernanda Miyuki Yamada; Hiroki Takahashi; Harlen Costa Batagelo; Jo ̃ao; Paulo Gois
Proc. SPIE 11766, International Workshop on Advanced Imaging Technology (IWAIT) 2021, 1176611, 1-6, 13 Mar. 2021, Peer-reviwed
International conference proceedings, English - Wafer Defect Pattern Classification Robust for Rotation
Yuki Okazaki; Hiroki Takahashi
Proc. SPIE 11766, International Workshop on Advanced Imaging Technology (IWAIT) 2021, 1176617, 1-6, 13 Mar. 2021, Peer-reviwed
International conference proceedings, English - Composition Presentation Based on Compositional Features for Photography Assistance
Taiki Akama; Masachika Suzuki; Hisao Kimura; Yoshio Asada; Keisuke Suzuki; Hiroki Takahashi
Proc. SPIE 11766, International Workshop on Advanced Imaging Technology (IWAIT) 2021, 117661I, 1-6, 13 Mar. 2021, Peer-reviwed
International conference proceedings, English - Points and Lines Based Feature Matching and 3D Reconstruction for Visual SLAM
Jiang Min; Hiroki Takahashi
Proceedings of the 2nd ASEAN-UEC Workshop on Energy and AI, 2pages, 21 Nov. 2020
International conference proceedings, English - Generation of Hiragana Ambigram Based on Character Structure Characteristics
Kazuki Inoue; Hiroki Takahashi
The Journal of the Institute of Image Electronics Engineers of Japan, 49, 4, 301-314, Oct. 2020, Peer-reviwed
Scientific journal, Japanese - An Extended Approach for the Automatic Solution of Tangram Puzzles Using Permutation Heuristics
Fernanda Miyuki Yamada; Hiroki Takahashi; Harlen Costa Batagelo; João Paulo Gois
Proceedings of NICOGRAPH International, 4pages, 05 Jun. 2020, Peer-reviwed
International conference proceedings, English - Automatic Focal Blur Segmentation Based on Difference of Blur Feature Using Theoretical Thresholding and Graphcuts
Natsuki Takayama; Hiroki Takahashi
Proceedings of Advanced Concepts for Intelligent Vision Systems(ACIVS), LNCS12002, 337-347, 10 Feb. 2020, Peer-reviwed
International conference proceedings, English - Diminished Reality in Textureless Scenes
Yuka Namboku; Hiroki Takahashi
Proceedings of IWAIT2020, 4D-1, 05 Jan. 2020, Peer-reviwed
International conference proceedings, English - Hiragana Ambigram Stroke Generation Based on Character Structure Transformation
Kazuki Inoue; Hiroki Takahashi
The First International Workshop on Control, Communication, and Multimedia 2019 (IWCCM2019), 40-43, 07 Dec. 2019, Peer-reviwed
International conference proceedings, English - Weakly-Supervised Learning for Continuous Sign Language Word Recognition Using DTW-Based Forced Alignment and Isolated Word HMM Adjustment
Natsuki Takayama; Hiroki Takahashi
IIEEJ Transaction on Image Electronics and Visual Computing, 7, 2, 88-96, Dec. 2019, Peer-reviwed
International conference proceedings, English - Kansei Retrieval of Living Room Images by Regularized Canonical Correlation Analysis
Naoko Kobayashi; Hisao Kimura; Yusuke Suzuki; Masachika Suzuki; Yoshio Asada; Hiroki Takahashi
Proceedings of the 1st ECTI UEC Workshop on AI and Application, 2pages, 06 Sep. 2019, Peer-reviwed
International conference proceedings, English - Kansei Retrieval of Living Room Images by Regularized Canonical Correlation Analysis
Naoko Kobayashi; Hisao Kimura; Yusuke Suzuki; Masachika Suzuki; Yoshio Asada; Hiroki Takahashi
Proceedings of the 6th IIEEJ International Workshop on Image Electronics and Visual Computing, 4B-4, 21 Aug. 2019, Peer-reviwed
International conference proceedings, English - Clothing Model Fitting for Laundry Folding Assistance
Megumi Kido; Hiroki Takahashi
Proceedings of NICOGRAPH International, 4pages, 05 Jul. 2019, Peer-reviwed
International conference proceedings, English - Sign Language Words Annotation Assistance using Binary Action Segmentation based on SVM and Graphcuts
Natsuki Takayama; Hiroki Takahashi
Proceedings of IWAIT-IFMIA2019, 10.1117/12.2521108, 06 Jan. 2019, Peer-reviwed
International conference proceedings, English - Multi-posture human extraction using coarse-to-fine method and human skeleton method
Yosuke Kinoshita; Hiroki Takahashi
Proceedings of IWAIT-IFMIA2019, 10.1117/12.2521502, 06 Jan. 2019, Peer-reviwed
International conference proceedings, English - Using transfer learning to classify images from real estate agent
Yang Cao; Shinichi Nunoya; Yusuke Suzuki; Masachika Suzuki; Yoshio Asada; Hiroki Takahashi
Proceedings of 10th International Conference on Graphics and Image Processing(ICGIP 2018), 1-6, 12 Dec. 2018, Peer-reviwed
International conference proceedings, English - Sign Words Annotation Assistance Using Japanese Sign Language Words Recognition
Natsuki Takayama; Hiroki Takahashi
Proceedings of Cyberworlds 2018, 1, 82-89, 03 Oct. 2018, Peer-reviwed
International conference proceedings, English - Annotation Assistance Using Japanese Sign Language Words Recognition
Natsuki Takayama; Hiroki Takahashi
Proceedings of NICOGRAPH International, 1page, 29 Jun. 2018, Peer-reviwed
International conference proceedings, English - Robust Gait Identification with Belongings From Back View
Toshiaki Hirooka; Hiroki Takahashi
Proceedings of International Workshop on Advanced Image Technology, 4pages, 09 Jan. 2018, Peer-reviwed
International conference proceedings, English - Illumination Estimation Based on Human Visual Characteristics for AR
Yuki Oyama; Hiroki Takahashi
Proceedings of International Workshop on Advanced Image Technology, 4pages, 09 Jan. 2018, Peer-reviwed
International conference proceedings, English - Performance Evaluation Criteria for Partial Blur Segmentation in Classification and Segmentation Contexts
Natsuki Takayama; Hiroki Takahashi
Last, IIEEJ Transaction on Image Electronics and Visual Computing, 5, 2, 123-133, Dec. 2017, Peer-reviwed
Scientific journal, English - Blur Map Generation Based on Local Natural Image Statistics for Partial Blur Segmentation
Natsuki TAKAYAMA; Hiroki TAKAHASHI
IEICE Transactions on Information and Systems, Institute of Electronics, Information and Communications Engineers (IEICE), E100.D, 12, 2984-2992, Dec. 2017, Peer-reviwed
Scientific journal, English - Non-planar Marker Matching with Partial Affine for AR
Tao Iwasaki; Hiroki Takahashi
Proceedings of the Fifth IIEEJ International Workshop on Image Electronics and Visual Computing, 5C-4, 28 Feb. 2017, Peer-reviwed
International conference proceedings, English - Back View Human Identification in Surveillance Videos
Fitria Yuningsihi; Hiroki Takahashi
Proceedings of International Workshop on Advanced Image Technology, 3C-5(4pages), 08 Jan. 2017, Peer-reviwed
International conference proceedings, English - Skin Analysis Using Sulcus Cutis Extraction
Yuriko Kobayashi; Christopher Tse; Chikako Shibata; Hiroki Takahashi
Proceedings of International Workshop on Advanced Image Technology, 4D-4(4pages), 08 Jan. 2017, Peer-reviwed
International conference proceedings, English - Multifaceted Maker Extraction with Feature Points for Vision-based Augmented Reality
Tao Iwasaki; Hiroki Takahashi
Proceedings of Joint Conference of IWAIT, 4B-1(4pages), 06 Jan. 2016, Peer-reviwed
International conference proceedings, English - Gaze Gesture Classification for Paging Operation in Mobile Device
Seiya Niii; Hiroki Takahashi
Proceedings of Joint Conference of IWAIT, 3B-3(4pages), 06 Jan. 2016, Peer-reviwed
International conference proceedings, English - Gesture-based Marking Operation for Slide Interface
HAYASAKA Reina; TAKAYAMA Natsuki; TAKAHASHI Hiroki
ITE Technical Report, The Institute of Image Information and Television Engineers, 40, 273-276, 2016, Generally, electronical slides are used in presentations and meetings. This paper propose a gesture-based marking operation for slide interface, because audiences sometimes miss important parts. Gestures are classified by using HMM (Hidden Markov Model). Some angles of arm joint and hand shape are used as feature value. The experiments are carried out using 3 kinds of HMMs. The first one is Left-to-Right HMM. The second one is combination of Left-to-Right HMM and Ergodic HMM. The last one is weighted combination of Left-to-Right HMM. The best classification performance is achieved by the last HMM with 85% accuracy.
Japanese - Target Selection Based on Gaze Likelihood in Gaze Input Interface
Fumihiro Kobayashi; Hiroki Takahashi
2016 8TH INTERNATIONAL CONFERENCE ON KNOWLEDGE AND SMART TECHNOLOGY (KST), IEEE, 249-252, 2016, Peer-reviwed, In recent years, computer device operation by gaze input has become popular. Some of the advantages are that those devices can be operated without hand. People with disabilities, therefore, are able to operate computers. This is also suitable for elderly people for whom it is easier to use gaze input than mice. It is, however, difficult to point to a target steadily by using eye gaze as the input, because eyes have the property of involuntary movement. It is, therefore, sometimes hard to perform stable target selection and may cause target selection errors. In this paper, gaze point is regarded to spread spatially and temporally. This paper proposes an icon selection method based on gaze likelihood. The proposed method has realized to improve the target selection accuracy. As a result, target selections are succeeded extremely from 44.7% to 84.5%. In conclusion, this paper shows a significance of the gaze likelihood.
International conference proceedings, English - MIB: A Bubble Maker Type Media Recorder
Takayuki Ono; Toshitaka Amaoka; Hiroki Takahashi
Proceedings NICOGRAPH International 2016, IEEE, 128-131, 2016, Peer-reviwed, MIB is a media recorder/player of sound and video handled with a gesture interface. The proposed technique allows users to capture and play audio-visual data by using gesture towards graphical bubbles. A graphical bubble, on which an image captured by a camera is mapped, is generated in real time when a user has captured an audio-visual datum. The captured datum is enclosed with the generated graphical bubble. Thereafter, the user can play/view the data by using gesture of touching and bursting a bubble. This research proposes new gesture-based interface for recording and viewing audio-visual data while playing with bubbles.
International conference proceedings, English - Efficient Ground Truth Generation based on Spatio-temporal Properties for Lane Prediction Model
Jun Shiwaku; Hiroki Takahashi
Proceedings of 10th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, 2, 455-460, 11 Mar. 2015, Peer-reviwed
International conference proceedings, English - Lane Prediction Model Based on Neural Network Using Time Series Data
Jun Shiwaku; Hiroki Takahashi
Proceedings of Joint Conference of IWAIT & IFMIA, No.540(4pages), 11 Jan. 2015, Peer-reviwed
International conference proceedings, English - Foreground object extraction using variation of blurs based on camera focusing
Natsuki Takayama; Hiroki Takahashi
2015 INTERNATIONAL CONFERENCE ON CYBERWORLDS (CW), IEEE, 125-132, 2015, Peer-reviwed, Image foreground object extraction is still challenging yet interesting topic in visual computing area. This paper proposes foreground extraction method based on one of the basic camera functions, focusing. A focus point and variation of blurs are extracted based on focusing, and these can be essential information to extract the foreground image. A focus point shows the rough position of the foreground, and variation of blurs becomes a distinctive image feature to segment foreground and background. The major contributions of this paper are developing a framework to extract a foreground object based on a camera function, and estimating the blur with the matching position between images using SIFT (Scale Invariant Feature Transform). SIFT is able to detect and describe image features which are invariant to scale, rotation and luminance changing. Moreover, scale-space extrema in SIFT can be used to estimate the variation of blurs. This is shown experimentally. Proposed foreground extraction is conducted in three steps. First, sparse variation of blurs between images is computed using SIFT. Next, the sparse variation of blurs is propagated using EAI (Edge Aware Interpolation) and a full variation of blur map is generated. Finally, foreground object extraction is obtained by GraphCut algorithm using a focus point as a constraint of the object. Experimental evaluation result shows improvement in performance of foreground object extraction using variation of blurs.
International conference proceedings, English - Gesture-based Multiuser Slide Interface with Stable Pointing Operation
Kazuma Miyanabe; Hiroki Takahashi
Proceedings of the Fourth IIEEJ International Workshop on Image Electronics and Visual Computing, 2C-5, 07 Oct. 2014, Peer-reviwed
International conference proceedings, English - Halftone Representation using Cutting Pattern for Choshi Design System
Natsuki Takayama; Hiroki Takahashi
Proceedings of NICOGRAPH International 2014, 65-70, 30 May 2014, Peer-reviwed
International conference proceedings, English - Paging Operation by Gaze Gesture for Mobile Devices
Naoya Takeuchi; Hiroki Takahashi
Proceedings of IWAIT(International Workshop on Advanced Image Technology), 627-632, Jan. 2014
International conference proceedings, English - Colored Papers Arrangement Method for Choshi Design System
Natsuki Takayama; Hiroki Takahashi
Proceedings of IWAIT(International Workshop on Advanced Image Technology), 387-392, Jan. 2014
International conference proceedings, English - Gesture-based Multiuser Slide Interface
Kazuma Miyanabe; Hiroki Takahashi
NICOGRAPH International 2013, 129-130, Jun. 2013
International conference proceedings, English - Ground Truth Generation based on Geometrical Features of Lane Makers
Jun Shiwaku; Hiroki Takahashi
NICOGRAPH International 2013, 133-134, Jun. 2013
International conference proceedings, English - Gait Feature Analysis for Personal De-identification
Genki Momose; Hiroki Takahashi
Proceedings of NICOGRAPH International 2012, 130-134, Jul. 2012, Peer-reviwed
International conference proceedings, English - Jump Movement Analysis on Mentally-retarded Students for Supporting Physical Exercise
Nagatoshi Hayabusa; Hiroki Takahashi
Proceedings of NICOGRAPH International 2012, 140-143, Jul. 2012, Peer-reviwed
International conference proceedings, English - Gaze Tracking for Mobile Devices Operation
Naoya Takeuchi; Hiroki Takahashi
Proceedings of NICOGRAPH International 2012, 149-152, Jul. 2012, Peer-reviwed
International conference proceedings, English - Jumping Exercise Support Application for Students with Down Syndrome and Autism on Special Needs Education
Atsumu Watanabe; Nagatoshi Hayabusa; Naoya Takeuchi; Hiroki Takahashi
Proceedings of IWAIT(International Workshop on Advanced Image Technology), 456-459, Jan. 2012
International conference proceedings, English - Shape-based 3D Retrieval by Primitive Combination Sketch Interface
Hiroaki Kozuka; Hiroki Takahashi
Proceedings of Triangle Symposium on Advanced ICT 2011, 185-188, Aug. 2011
International conference proceedings, English - Non-invasive Sagittal Pelvic Inclination Estimation by Using Stable Attached Markers
Nagatoshi Hayabusa; Hiroki Takahashi
Proceedings of Triangle Symposium on Advanced ICT 2011, 225-228, Aug. 2011
International conference proceedings, English - Non-invasive Sagittal Pelvic Inclination Estimation
Nagatoshi Hayabusa; Hiroki Takahashi
Proceedings of NICOGRAPH International 2011, P11, Jun. 2011
International conference proceedings, English - First-person Perspective See-through Using AR Marker
Atsumu Watanabe; Hiroki Takahashi
Proceedings of NICOGRAPH International 2011, P12, Jun. 2011
International conference proceedings, English - "Cho-Shi" animation based on traditional Chinese handmade paper texture
Yanxiang Zhang; Chunyong Yang; Fangbemi Abassin; Natsuki Takayama; Shunbing Meng; Hiroki Takahashi
Proceedings - 2011 2nd International Conference on Culture and Computing, Culture and Computing 2011, 161-162, 2011, Peer-reviwed, "Cho-Shi" is one form of Japanese carving art. It is a technique that uses a composition of papers of different colors with a certain thickness to carve, and produce concave and convex shapes while expressing colors. This form of art makes a two dimensional picture take a three-dimensional structure, giving an experience which is different from the traditional picture. However, because "Cho-Shi" has a complex structure, and its production steps are complicated, it requires producer to have some knowledge of art and time. The authors proposed a computer-aided "Cho-Shi" system, which outputs paper layers and mask for carving, according to images [1]. This greatly simplifies the complexity of carving and shortens the carving time. This paper extends the method to generate animation. Moreover, Chinese traditional hand-made paper textures are applied for the animation to express a novel form and this paper tries to fuse Japanese and Chinese art works, essentially, it tries to fuse old and new styles of media. © 2011 IEEE.
International conference proceedings, English - Freckle Feature Analysis for Face Texture Synthesis
Rui Guo; Hiroki Takahashi
Proceedings of Triangle Symposium on Advanced ICT 2010, 256-261, Oct. 2010
International conference proceedings, English - Analysis and Synthesis of Human Skin Venation Distribution
Rui Guo; Hiroki Takahashi
NICOGRAPH International 2010, 80-85, Jun. 2010
International conference proceedings, English - Choshi generation system by color and shape stylization
Shubing Meng; Hiroki Takahashi
NICOGRAPH International 2010, 107-114, Jun. 2010
International conference proceedings, English - Transpiring the road surface marking line Visualization for drivers at nighttime
Yoshiya Iwaki; Hiroki Takahashi
NICOGRAPH International 2010, 37-42, Jun. 2010
International conference proceedings, English - Watermark Extraction from Partial Image for Mobile Digital Watermarking
Misato Mochizuki; Hiroki Takahashi
NICOGRAPH International 2010, 167-168, Jun. 2010
International conference proceedings, English - 3D Model Retrieval by using Primitive-based Sketch
Hiroaki Kozuka; Hiroki Takahashi
NICOGRAPH International 2010, 165-166, Jun. 2010
International conference proceedings, English - Saliency-Based Candidate Inspection Region Extraction in Tape Automated Bonding
Martina Duemcke; Hiroki Takahashi
ADVANCES IN DATA MINING: APPLICATIONS AND THEORETICAL ASPECTS, SPRINGER-VERLAG BERLIN, 6171, 186-+, 2010, Peer-reviwed, Electronic circuits are composed of components connected by traces which conduct the current. While the interconnections between the components can be created by assembling individual pieces of wire, it is nowadays common to use printed circuit boards. Tape automated bonding (TAB) is a technique to assemble chips and printed circuit boards. Because TAB become smaller, their inspection methods are required to adapt to the decreasing size of the electric circuits' pattern. An image of a TAB is taken during time manufacturing process and analysed using image processing algorithms to inspect it for flaws in its pattern. This paper proposes an algorithm to find candidate inspection regions in a TAB pattern based on visual saliency. Orientation information contained in the image is processed to detect probable error regions and exclude correct regions from further inspection. The algorithm finds all the flaws in an image and in the case of regular patterns, marks only 5% of the image pixels as belonging to a candidate inspection region. The results show that a. saliency-based approach is applicable on the task of finding flaws in the pattern of an electric circuit.
International conference proceedings, English - Skin-anatomy based face texture image synthesis by skin feature distribution analyzing method
Rui Guo; Hiroki Takahashi
Proceedings - 5th International Conference on Frontier of Computer Science and Technology, FCST 2010, 136-141, 2010, Peer-reviwed, This paper investigates solutions to improvement of realistic rendering quality of CG (Computer Graphics) character face. In order to manipulate face skin feature distribution, based on bio-anatomic structure, skin surface is classified into 3 layers(Internal, Regular and Local layer) to control skin base color, surface cellular venation level and noise distribution like freckle, respectively. Moreover, for the feature best re-targeting from, real human to virtual character, a new face segmentation method is introduced by analyzing and overlaying the appropriate feature to the deserved area. By doing all above, a specific transformation from, real human face skin data to virtual character is proposed which is meaningful for the synthesis of CG texture. © 2010 IEEE.
International conference proceedings, English - Choshi Design System from 2D Images
Natsuki Takayama; Shubing Meng; Takahashi Hiroki
ENTERTAINMENT COMPUTING - ICEC 2010, SPRINGER-VERLAG BERLIN, 6243, 358-365, 2010, Peer-reviwed, This paper proposes a Choshi design system. Choshi is a new method for carving of paper, which is uneven 3D shape and unique colors of papers. Choshi, derived from carving overlaid colored papers, has the following three features:
1. Each layer consists of a single piece of paper of one color.
2. The color must be selected from a number of existing colors.
3. Choshi has an overlaid structure where carved papers are overlaid on other carved papers.
The goal of the proposed Choshi design system has two issues: to enable a wider variety of people to easily and successfully create Choshi art, and to reduce the difficulty and tedium, of creating a Choshi art piece.
International conference proceedings, English - Saliency-based Algorithm for Extracting Candidate Inspection Regions in Tape Automated Bonding
Martina Dumcke; Akiko Takakura; Mohammad Ali Akbari; Hiroki Takahashi
Proceedings of NICOGRAPH International 2009, 126-130, Jun. 2009
International conference proceedings, English - VRML-Ajax Based Web3D Movie-Shooting Information-Visualization System
Rui Guo; Hiroki Takahashi; Masakatsu Kaneko
The International Workshop on Modern Science and Technology 2008(IWMST2008), 373-379, Nov. 2008
International conference proceedings, English - Sagittal Pelvic Inclination Measurement for an Exercise Support System
Nagatoshi Hayabusa; Hiroki Takahashi
Proceedings of NICOGRAPH International 2008, 121-127, May 2008
International conference proceedings, English - Sketch-based evaluation of image segmentation methods
David Gavilan; Hiroki Takahashi; Suguru Saito; Masayuki Nakajima
IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS, IEICE-INST ELECTRONICS INFORMATION COMMUNICATIONS ENG, E90D, 1, 156-164, Jan. 2007, Peer-reviwed, A method for evaluating image segmentation methods is proposed in this paper. The method is based on a perception model where the drawing act is used to represent visual mental percepts. Each segmented image is represented by a minimal set of features and the segmentation method is tested against a set of sketches that represent a subset of the original image database, using the Mahalanobis distance function. The covariance matrix is set using a collection of sketches drawn by different users. The different drawings are demonstrated to be consistent across users. This evaluation method can be used to solve the problem of parameter selection in image segmentation, as well as to show the goodness or limitations of the different segmentation algorithms. Different well-known color segmentation algorithms are analyzed with the proposed method and the nature of each one is discussed. This evaluation method is also compared with heuristic functions that serve for the same purpose, showing the importance of using users' pictorial knowledge.
Scientific journal, English - Mobile Image Retrieval using Morphological Color Segmentation
David Gavilan; Hiroki Takahashi; Suguru Saito; Masayuki Nakajima
3rd International Conference on Mobile and Ubiquitous Computing, IPSJ, pp.51-58, Oct. 2006, Peer-reviwed
International conference proceedings, English - Extracting Objects Using Contour Evolutions in Edge-based Object Tracking
Hiroyuki Tsuji; Shinji Tokumasu; Hiroki Takahashi; Masayuki Nakajima
Journal of Advanced Computational Intelligence and Intelligent Informatics(JACIII), 10, 3, 362-371, May 2006, Peer-reviwed
Scientific journal, English - Spherical parameterization and geometry image-based 3D shape similarity estimation (CGS 2004 special issue)
H Laga; H Takahashi; M Nakajima
VISUAL COMPUTER, SPRINGER, 22, 5, 324-331, May 2006, Peer-reviwed, In this paper, we describe our preliminary findings in applying the spherical parameterization and geometry images to the task of 3D shape matching. View-based techniques compare 3D objects by comparing their 2D projections. However, it is not trivial to choose the number of views and their settings. Geometry images overcome these limitations by mapping the entire object onto a spherical or planar domain. We make use of this property to derive a rotation invariant shape descriptor. Once the geometry image encoding the object's geometric properties is computed, a 1D rotation invariant descriptor is extracted using the spherical harmonic analysis. The parameterization process guarantees the scale invariance, while its coarse-to-fine nature allows the comparison of objects at different scales. We demonstrate and discuss the efficiency of our approach on a collection of 120 three-dimensional models.
Scientific journal, English - Morphological Sieves on Layered Images for Image Segmentation
David Gavilan; Hiroki Takahashi; Suguru Saito; Masayuki Nakajima
Nicograph International 2006, (on CD), May 2006, Peer-reviwed
International conference proceedings, English - Analyzing the Importance of Different Facial Feature Points in Non-identical Facial Recognition
Akbari Mohammad Ali; Hiroki Takahashi; Masayuki Nakajima
Proc. of IWAIT(InternationalWorkshop on Advanced Image Technology) 2006, The Institute of Electronics, Information and Communication Engineers, 105, 500, 180-185, Jan. 2006, There is wide application defined for face recognition in computer vision domain. However it is usually referring to identical face recognition to identify the exact person with that face. But there is another facial recognition or actually facial perception task which is being done by people during their daily interactions. It can be named as non-identical facial recognition which tries to process other personal characteristics like gender or age that can affect the method or context of the interaction. In this paper it is tried to analyze the importance of different facial feature points in this kind of process when there is no special target for facial comparison. For this purpose a dataset of facial images with different personal characteristics were manually marked. Then several measurements have been extracted automatically based on these landmarks. Consequently significance of the discrimination and importance analysis of these features was done by a covariance based method. The statistical results of this analysis can be used in designing more sophisticated human computer interactions relying on understanding some personal characteristics of the person on the opposite side.
International conference proceedings, English - Spherical wavelet descriptors for content-based 3D model retrieval
Hamid Laga; Hiroki Takahashi; Masayuki Nakajima
IEEE INTERNATIONAL CONFERENCE ON SHAPE MODELING AND APPLICATIONS 2006, PROCEEDINGS, IEEE COMPUTER SOC, 75-+, 2006, The description of 3D shapes with features that possess descriptive power and invariant under similarity transformations is one of the most challenging issues in content based 3D model retrieval. Spherical harmonics-based descriptors have been proposed for obtaining rotation invariant representations. However spherical harmonic analysis is based on latitude-longitude parameterization of a sphere which has singularities at each pole. Consequently, features near the two poles are over represented while features at the equator are under-sampled, and variations of the north pole affects significantly the shape function. In this paper we discuss these issues and propose the usage of spherical wavelet transform as a tool for the analysis of 3D shapes represented by functions on the unit sphere. We introduce three new descriptors extracted from the wavelet coefficients, namely: (1) a subset of the spherical wavelet coefficients, (2) the L-1 and, (3) the L-2 energies of the spherical wavelet sub-bands. The advantage of this tool is three fold; First, it takes into account feature localization and local orientations. Second, the energies of the wavelet transform are rotation invariant. Third, shape features are uniformly represented which makes the descriptors more efficient. Spherical wavelet descriptors are natural extension of 3D Zernike moments and spherical harmonics. We evaluate, on the Princeton Shape Benchmark, the proposed descriptors regarding computational aspects and shape retrieval performance.
International conference proceedings, English - Evolving Creatures with a Deformable Body
Srisombut Preechaya; Hiroki Takahashi; Masayuki Nakajima
Proc. of IWAIT(InternationalWorkshop on Advanced Image Technology) 2006, 349-354, Jan. 2006
International conference proceedings, English - Sketch-based Fine-tuning of Image Segmentation Methods
David Gavilan Ruiz; Hiroki Takahashi; Suguru Saito; Masayuki Nakajima
Proc. of IWAIT(InternationalWorkshop on Advanced Image Technology) 2006, 393-398, Jan. 2006
International conference proceedings, English - Generation of Open-door-action According to Hip Trajectory using Continuous HMM Technique
Yuuki Hirakawa; Suguru Saito; Hiroki Takahashi; Masayuki Nakajima
Proc. of IWAIT(InternationalWorkshop on Advanced Image Technology) 2006, The Institute of Electronics, Information and Communication Engineers, 105, 500, 550-555, Jan. 2006, Opening a door and going through it is a trivial action in ordinary life. For a virtual agent, however, actions like approaching the doorknob from an arbitrary position, pulling it, and following the door movement, all have to be taken into account in order to generate the computer graphics animation for that action. In this paper, we make use of machine learning techniques which can build models for the animation synthesis of opening a door. First we use motion capture system to acquire motion data for the typical action. The data set along with restraint conditions are fed into continuous Hidden Markov Models (HMMs) which can learn the action of opening a door. Restraint conditions are what should be considered while moving, such that the foot on the floor must not slip. To generate a new animation, the hip trajectory of a character is applied to the model, then the highest probability of state transitions in HMMs is calculated and the corresponding sequence to the transitions is generated automatically. As a result, we generate a door opening action which consists of parallel and serial motions.
International conference proceedings, English - Body Calibration for Motion Capture System
Satoshi Kondoh; Suguru Saito; Hiroki Takahashi; Masayuki Nakajima
Proc. of IWAIT(InternationalWorkshop on Advanced Image Technology) 2006, 563-568, Jan. 2006
International conference proceedings, English - High-resolution 3D Shape Reconstruction and Evaluation using a Flatbed Scanner
Kazuhiro Sudo; Akihiro Yamaguchi; Suguru Saito; Hiroki Takahashi; Masayuki Nakajima
Proc. of IWAIT(InternationalWorkshop on Advanced Image Technology) 2006, The Institute of Electronics, Information and Communication Engineers, 105, 501, 779-784, Jan. 2006, This paper presents a method to reconstruct the 3D shape of an object using a flatbed scanner and a transparency sheet on which stripe patterns are printed. When scanning an object on the transparency sheet, the stripes generate a growing shadow according to the depth of the object surface. Estimating the depth of a point from the shadow's length allows us to reconstruct the 3D shape. In addition, we correct the distortion that occurs when scanning on the sides on the scanner, as a flatbed scanner uses cylindrical optics. Hence we can use a wider area of the scanner's plane, leading to more accurate results. We evaluate the precision of our method with two examples, and we show that even elaborate details are precisely captured by our system.
International conference proceedings, English - Spherical wavelet descriptors for content-based 3D model retrieval
Hamid Laga; Hiroki Takahashi; Masayuki Nakajima
IEEE INTERNATIONAL CONFERENCE ON SHAPE MODELING AND APPLICATIONS 2006, PROCEEDINGS, IEEE COMPUTER SOC, 75-+, 2006, Peer-reviwed, The description of 3D shapes with features that possess descriptive power and invariant under similarity transformations is one of the most challenging issues in content based 3D model retrieval. Spherical harmonics-based descriptors have been proposed for obtaining rotation invariant representations. However spherical harmonic analysis is based on latitude-longitude parameterization of a sphere which has singularities at each pole. Consequently, features near the two poles are over represented while features at the equator are under-sampled, and variations of the north pole affects significantly the shape function. In this paper we discuss these issues and propose the usage of spherical wavelet transform as a tool for the analysis of 3D shapes represented by functions on the unit sphere. We introduce three new descriptors extracted from the wavelet coefficients, namely: (1) a subset of the spherical wavelet coefficients, (2) the L-1 and, (3) the L-2 energies of the spherical wavelet sub-bands. The advantage of this tool is three fold; First, it takes into account feature localization and local orientations. Second, the energies of the wavelet transform are rotation invariant. Third, shape features are uniformly represented which makes the descriptors more efficient. Spherical wavelet descriptors are natural extension of 3D Zernike moments and spherical harmonics. We evaluate, on the Princeton Shape Benchmark, the proposed descriptors regarding computational aspects and shape retrieval performance.
International conference proceedings, English - ハングルの構造特徴を用いた情景画像からのハングル文字列領域抽出
高橋裕樹; 金大祐; 中嶋正之
The IEICE Transactions on Information and Systems, The Institute of Electronics, Information and Communication Engineers, J88-D-II, 9, 1808-1816, Sep. 2005, Peer-reviwed, 本論文では, ディジタルカメラで撮影した画像中のハングルを対象とした文字列領域の抽出を行う手法について検討を行う. ハングルの構造特徴を利用し, エッジ特徴と色特徴から段階的にハングルを構成する字素を抽出することによって, 情景画像から文字列を抽出する手法を提案する. エッジ画像からは, 字素としての形状の単純さを満たす条件を用いてテクスチャやノイズを多く含む領域を削除した後, 字素の形状特徴を利用して字素エッジの抽出を行う. 次に, 字素エッジに対する外接方形を対象範囲とし, 局所的な輝度分布から字素と背景の分離を行う. その後, 抽出された字素領域の代表色を用いた色空間でのクラスタリングを行うことによって, 画像全体の色分布の影響を受けにくい文字列領域の抽出を行うことができる. 任意の条件で撮影した実験用画像60枚に対して文字列を抽出した結果, 文字列中の85.6%の文字が抽出でき, 文字列の再現率60.8%, 精度45.2%を得た. また, 評価用の画像20枚に対し, 82.7%の文字抽出率, 文字列抽出の再現率46.2%, 精度46.2%を得た.
Scientific journal, Japanese - Text Image Enhancement in Scenery Images for Degraded Char- acter Recognition using DCT
Hiroki Takahashi; Masayuki Nakajima
The Journal of the Society for Art and Science, 4, 3, 101-107, Sep. 2005, Peer-reviwed
Scientific journal, English - 非等方拡散法に基づく空間平滑化フィルタの構築に関する基礎検討
辻裕之; 徳増眞司; 高橋裕樹; 中嶋正之
The IEICE Transactions on Information and Systems, The Institute of Electronics, Information and Communication Engineers, J88-D-II, 6, 1024-1034, Jun. 2005, Peer-reviwed, 低ビットレート映像符号化に使用されるプレフィルタは, 平滑化による情報量の削減を実現すると同時に, 視覚的に重要なエッジをなるべく保存する非線形な性質をもつことが望ましい. そこで本論文では, 非等方拡散法を利用してエッジ保存型の平滑化フィルタを構築するための基礎検討を行った. Perona-Malikによる従来の非等方拡散法(PMD)を平滑化フィルタとして使用した場合, 輝度こう配の大きなノイズの残留, 過度のエッジ強調などの問題があることが知られている. 本論文では, これらを解決するためにエッジ停止関数が満たすべき条件を明らかにし, それに基づいて具体的な関数の導出を行った. また, シミュレーション実験を通して, 今回導出したエッジ停止関数から得られる非等方拡散法によって上述の問題が解決されることを確認した. 更に, 低ビットレート映像符号化のプレフィルタとしての応用を想定し, 本フィルタによる情報量削減効果についても実験を行い, 提案手法の有効性を確認した.
Scientific journal, Japanese - Evaluating Color Segmentation Methods with Mental Percepts
David Gavilan Ruiz; Hiroki Takahashi; Suguru Saito; Masayuki Nakajima
CGI(Conputer Graphics International)2005, poster, Jun. 2005, Peer-reviwed
International conference proceedings, English - Scale-space processing of point-sampled geometry for efficient object segmentation
H Laga; H Takahashi; M Nakajima
IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS, IEICE-INST ELECTRONICS INFORMATION COMMUNICATIONS ENG, E88D, 5, 963-970, May 2005, Peer-reviwed, In this paper, we present a novel framework for analyzing and segmenting point-sampled 3D objects. Our algorithm computes a decomposition of a given point set surface into meaningful components, which are delimited by line features and deep concavities. Central to our method is the extension of the scale-space theory to the three-dimensional space to allow feature analysis and classification at different scales. Then, a new surface classifier is computed and used in an anisotropic diffusion process via partial differential equations (PDEs). The algorithm avoids the misclassifications due to fuzzy and incomplete line features. Our algorithm operates directly on points requiring no vertex connectivity information. We demonstrate and discuss its performance on a collection of point sampled 3D objects including CAD and natural models. Applications include 3D shape matching and retrieval, surface reconstruction and feature preserving simplification.
Scientific journal, English - Color Blobs-based Image Retrieval in Broad Domains
David Gavilan Ruiz; Hiroki Takahashi; Masayuki Nakajima
Proc. of IWAIT(International Workshop on Advanced Image Technology) 2005, 115-120, Jan. 2005
International conference proceedings, English - A study of swimmimg animation using stereo images
Suma Noji; Hiroki Takahashi; Masayuki Nakajima
Proc. of IWAIT(International Workshop on Advanced Image Technology) 2005, 505-508, Jan. 2005
International conference proceedings, English - WARAJI Foot-Driven Navigation Interfaces for Virtual Reality Applications on CAVE
Barrera Salvador; Hiroki Takahashi; Masayuki Nakajima
Proc. of IWAIT(International Workshop on Advanced Image Technology) 2005, The Institute of Electronics, Information and Communication Engineers, 104, 545, 311-316, Jan. 2005, Presently Technological limitations on current interfaces have made researchers to develop new devices to interact with objects in the virtual environment. The goal of this project is to develop and build a hands-free navigation system to be integrated into virtual environments. One of the most important fields in virtual realty (VR) research, is the development of systems that allow the user to interface with the virtual environment. The most intuitive method for moving through a virtual landscape is by walking. Systems ranging from different platforms have already been implemented to produce virtual walking; however, these systems have been designed primarily for use with head mounted display systems. We believe that hands-free navigation, unlike the majority of navigation techniques based on hand motions, has the greatest potential for maximizing the interactivity of virtual environments, due to more direct motion of the feet.
International conference proceedings, English - Detection of Grasping Position from an Object for Autonomous Agents in the Virtual World
Fumihito Kyota; Hiroki Takahashi; Suguru Saito; Masayuki Nakajima
Proc. of IWAIT(International Workshop on Advanced Image Technology) 2005, 263-268, Jan. 2005
International conference proceedings, English - Investigation of Invariant Color Models for Text Detection from Scenery Images
Yang Xiaoheng; Hiroki Takahashi; Masayuki Nakajima
Proc. of IWAIT(International Workshop on Advanced Image Technology) 2005, The Institute of Electronics, Information and Communication Engineers, 104, 544, 215-218, Jan. 2005, This paper introduces an investigation of the color information to get good representation of text part from natural scenes. Two different categories are discussed based on the experiment results. Edge detection for text images is briefly reviewed to show a robust method for detecting the text edges in natural scenes, which is against the effects caused by shadow or highlight. The other is to try to find some color models, which can get good representation on the text part by applying a series of morphological operations under different image transitions. Many color models including the invariant color models proposed by us are tested to find the robust ones under arbitrary image conditions. For text detection tasks, both the clean representation and the intact edge are useful information.
International conference proceedings, English - Scale-Space Framework for E±cient Segmentation of Point-Sampled Geometry
Hamid Laga; Hiroki Takahashi; Masayuki Nakajima
Proc. of IWAIT(International Workshop on Advanced Image Technology) 2005, 481-486, Jan. 2005
International conference proceedings, English - Effect of Frame Delay on Stereoscopic Vision: Relationship between Frame Delay and Combinations of Movements of an Object
Yoshiyasu Yui; Hiroki Takahashi; Masayuki Nakajima
Proc. of IWAIT(International Workshop on Advanced Image Technology) 2005, The Institute of Electronics, Information and Communication Engineers, 104, 545, 375-380, Jan. 2005, We have investigated the effect of frame delay on stereoscopic vision for an object with various movements in a virtual environment. The effect on stereoscopic vision was measured by using the method of limits by changing the delay (i.e., the number of frames) between the left-eye image and the right-eye image to determine changes in the viewer's stereoscopic vision. The measurements clarify the change tendencies with a maximum number of delays and allow the viewer to enjoy clear stereoscopic images when frame delay occurs.
International conference proceedings, English - Region graph based text extraction from outdoor images
H Takahashi; M Nakajima
THIRD INTERNATIONAL CONFERENCE ON INFORMATION TECHNOLOGY AND APPLICATIONS, VOL 1, PROCEEDINGS, IEEE COMPUTER SOC, 680-685, 2005, Peer-reviwed, A graph-based texts extraction scheme using region similarities is proposed. In graph-based texts extraction method, region graph is generated based on the extracted character element regions from edge images. ne edge weights of the graph are defined by their representative colors, positions, area sizes and aspect ratios of their bounding boxes. The MST is obtained from the graph, since sets of similar regions are the most significant factors in texts extraction techniques. Then, texts blocks with small edge weights are obtained from the MST Finally, texts regions which satisfy texts conditions are extracted from these subsets. The proposed method extracts texts under complex shadows and low contrast images.
International conference proceedings, English - Sketch-based perception model for evaluating color segmentations
David Gavilan; Hiroki Takahashi; Suguru Saito; Masayuki Nakajima
Proceedings - APGV 2005: 2nd Symposium on Applied Perception in Graphics and Visualization, 167, 2005, Peer-reviwed
International conference proceedings, English - Estimating object contours from binary edge images
H Tsuji; S Saito; H Takahashi; M Nakajima
2005 INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), VOLS 1-5, IEEE, 3049-3052, 2005, Peer-reviwed, We propose a new method of estimating object contours from thresholded binary edge images. Our work is motivated by the edge-based video object plane (VOP) generation proposed by Meier, targeted at MPEG-4 object-based video coding. When objects are detected in the form of binary edge images, we have to estimate the complete object contour from edges that do not form a closed contour. The proposed method is designed to carry out this task using only binary edge images. To achieve this, we first introduce a probability field representing the probability that the object contour lies on each pixel, and then take a modified geodesic active contour approach to make the initial contour converge with the contour of the object according to the probability field.
International conference proceedings, English - Discerning Advisor: An intelligent advertising system for clothes considering skin color
MA Akbari; H Takahashi; M Nakajima
2005 INTERNATIONAL CONFERENCE ON CYBERWORLDS, PROCEEDINGS, IEEE COMPUTER SOC, 202-209, 2005, Peer-reviwed, Facial perception is what usually human beings do during their daily communications. They may adjust and change the method or contents of the interaction based on this perception. One of the most probable places of this process is during the personalized advertising that is highly under consideration nowadays. Here as a sample of this kind of systems it is tried to propose a system named 'Discerning Advisor' for suggesting clothing fashion considering matching colors with the perception of skin color from the face. This is a considerable point by the fashion designers and advisors which the system will be trained by their knowledge.
For this purpose a comprehensive study has been done on the human skin color model and its variations around the world and among different races. A neural network based skin detector was designed and trained to extract the skin area of the images automatically. It was applied on a large dataset of digital images containing 1000 faces of peoples of almost all races from 23 cities around the world. Calculating indicator color for each individual gave the ability of analysis of distribution and fuzzy-clustering the skin color. Finally the clustering result was used in classification of the skin color that can be matched with the suggested colors from the fashion designers.
International conference proceedings, English - Object Extraction Method Based on Contour Evolutions in Edge-based Object Tracking
Hiroyuki Tsuji; Shinji Tokumasu; Hiroki Takahashi; Masayuki Nakajima
the 5th International Conference on Intelligent Tech- nologies(InTech'04), CD-ROM proceeding, Dec. 2004, Peer-reviwed
International conference proceedings, English - Toward anthropometrics simulation of face rejuvenation and skin cosmetic
A Bastanfard; O Bastanfard; H Takahashi; M Nakajima
COMPUTER ANIMATION AND VIRTUAL WORLDS, WILEY-BLACKWELL, 15, 3-4, 347-352, Jul. 2004, Peer-reviwed, Facial rejuvenation is the process of reversing the aging effects on the human face digitally. This paper generalizes a new approach for facial rejuvenation in adults image. Applications of facial rejuvenation are widespread. They include face recognition, education, entertainment, telecommunications, Psychology, criminal objects, Cosmetic arts and it can be used as an aid for medical cosmetics surgery and the reconstruction of the face. This paper proposes a novel facial rejuvenation modeling algorithm with two techniques. These techniques discuss the facial deformation based on the face anthropometrics theory and remove wrinkles based on what we called wrinkles inpainting. For example if we have been given a few different faces, we need to be able to compare the difference between the facial characteristics of the youth and the aged, then from there onwards, define a set of outlines which are going to be the basis of the simulation of Face Rejuvenation. The first is the geometric deformation details like skin texture, which differs between the aged and the youth. The second is anthropometrics data change. It was developed in the face anthropometrics measurement theory. Then together with warping technique we map the characteristics to any other particular persons' face in order to generate more expressive and convincing facial rejuvenation. The original contribution and advantage of this paper are that, the proposed methods are simple to implement, reliable, in which they required only one source image without needing to collect a lot of images and their computation are fast for interactive environment. Copyright (C) 2004 John Wiley Sons, Ltd.
Scientific journal, English - Text Extraction from Natural Scenes based on Investigation of Color Information
Yang Xiaoheng; Hiroki Takahashi; Masayuki Nakajima
NICOGRAPH International, 143-148, May 2004
International conference proceedings, English - 光線ボリュームバッファを用いたボリュームとポリゴンの混在シーンのレンダリング方法
梶原景範; 高橋裕樹; 中嶋正之
芸術科学会論文誌, 3, 1, 69-75, Mar. 2004, Peer-reviwed
Scientific journal, Japanese - A Method of Rendering Scenes Including Volumetric Objects Using Ray-Volume Buffers --Expansion to Perspective Projection--
Kagenori Kajihara; Hiroki Takahashi; Masayuki Nakajima
Proc. of IWAIT(International Workshop on Advanced Image Technology) 2004, 375-380, Jan. 2004
International conference proceedings, English - Garment Drape Image Simulation by Using Gabor Wavelets
Azam Bastanfard; Hiroki Takahashi; Masayuki Nakajima
Proc. of IWAIT(International Workshop on Advanced Image Technology) 2004, 323-328, Jan. 2004
International conference proceedings, English - A Spatio-temporal Prefiltering Scheme Based on Anisotropic Diffusion in Low Bitrate Video Coding
Hiroyuki Tsuji; Shinji Tokumasu; Hiroki Takahashi; Masayuki Nakajima
Proc. of IWAIT(International Workshop on Advanced Image Technology) 2004, 141-146, Jan. 2004
International conference proceedings, English - Hologram Works on Indefinite Object Image --Contour Extraction of a Soap Bubble Image--
Setsuko Ishii; David Gavilan Ruiz; Hiroki Takahashi; Masayuki Nakajima
Proc. of IWAIT(International Workshop on Advanced Image Technology) 2004, The Institute of Image Information and Television Engineers, 26, 387-390, Jan. 2004, The purpose of this study is to investigate techniques of generating a realistic 3D soap bubble model which we aim to apply to a holographic image. Holography is a technology that records 3D images by using laser light. As technologies have been evolving, it has become possible to record various images as holograms, for example, momentary scenes and synthetic images. On the other hand, soap bubbles in natural environment are very attractive subjects for hologram because of their features, constant transformation, complex interference colors and reflection. However, shooting such real object directly to make a hologram is still not possible. Hence, we aim to make a hologram from the realistic 3D soap bubble model. There are two different approaches to get realistic model, which are based on physical models and real pictures. However, the first one is too complex because of the large amount of factors to be considered. Thus, we try to build a model by using real pictures. As a first stage, we investigate the technique of extraction of the soap bubble in the real picture. In this paper, we present a way of extracting soap bubble contours by using g-snakes (Generalized Active Contour Models).
International conference proceedings, English - Geometry image matching for similarity estimation of 3D shapes
H Laga; H Takahashi; M Nakajima
COMPUTER GRAPHICS INTERNATIONAL, PROCEEDINGS, IEEE COMPUTER SOC, 490-496, 2004, In this paper we describe our preliminary findings in applying the spherical parametrization and geometry images to the task of 3D shape matching and similarity based comparison of polygon soup models. Unlike traditional approach where multiple 2D views of the same object are required to capture the relevant geometry features, our proposed technique uses spherical parametrization and geometry images for 3D shape matching. This technique reduces the problem to the 2D space without computing 2D projections and guaranties the preservation of small details. Moreover we take advantage from the hierarchical nature of the parametrization process, through the Progressive Mesh simplification, to derive a multiresolution analysis technique. Our proposed algorithm is invariant to similarity transformations such as rotation and scaling. The efficiency of this approach is discussed through a set of experiments.
International conference proceedings, English - Geometry image matching for similarity estimation of 3D shapes
H Laga; H Takahashi; M Nakajima
COMPUTER GRAPHICS INTERNATIONAL, PROCEEDINGS, IEEE COMPUTER SOC, 490-496, 2004, Peer-reviwed, In this paper we describe our preliminary findings in applying the spherical parametrization and geometry images to the task of 3D shape matching and similarity based comparison of polygon soup models. Unlike traditional approach where multiple 2D views of the same object are required to capture the relevant geometry features, our proposed technique uses spherical parametrization and geometry images for 3D shape matching. This technique reduces the problem to the 2D space without computing 2D projections and guaranties the preservation of small details. Moreover we take advantage from the hierarchical nature of the parametrization process, through the Progressive Mesh simplification, to derive a multiresolution analysis technique. Our proposed algorithm is invariant to similarity transformations such as rotation and scaling. The efficiency of this approach is discussed through a set of experiments.
International conference proceedings, English - "Hands-free navigation methods for moving through a virtual landscape walking interface virtual reality input devices"
S Barrera; H Takahashi; M Nakajima
COMPUTER GRAPHICS INTERNATIONAL, PROCEEDINGS, IEEE COMPUTER SOC, 388-394, 2004, Peer-reviwed, Technological limitations on current interfaces have made researches to develop new devices to interact with objects in the virtual environment. The goal of this project is to develop and build a hands-free navigation system to be integrated into virtual environments. One of the most important fields in virtual realty (VR) research, is the development of systems that allow the user to interface with the virtual environment. The most intuitive method for moving through a virtual landscape is by walking. The implementation of a walking interface for a virtual reality system also allows a greater range of biomechanical experimentation and game research. Systems ranging from different platforms have already been implemented to produce virtual walking; however these systems have been designed primarily for use with head mounted display systems. We believe that hands-free navigation, unlike the majority of navigation techniques based on hand motions, has the greatest potential for maximizing the interactivity of virtual environments, due to more direct motion of the feet. To make this possible, we created a new and simple device using acceleration sensors to detect ankle movements within the virtual environment. The acceleration sensors are attached to the foot and detect movement based on direction for three different angles. This experimentation could prove beneficial in future virtual gaming. Validation of our approach is given by discussion and illustration of some results.
International conference proceedings, English - Scale-space processing of point-sampled geometry for efficient 3D object segmentation
H Laga; H Takahashi; M Nakajima
2004 INTERNATIONAL CONFERENCE ON CYBERWORLDS, PROCEEDINGS, IEEE COMPUTER SOC, 377-383, 2004, Peer-reviwed, In this paper we present a new framework for analyzing and segmenting point-sampled 3D objects. Our method first computes for each surface point the surface curvature distribution by applying the Principal Component Analysis on local neighborhoods with different sizes. Then we model in the four dimensional space the joint distribution of surface curvature and position features as a mixture of Gaussians using the Expectation Maximization algorithm. Central to our method is the extension of the scale-space theory from the 2D domain into the three-dimensional space to allow feature analysis and classification at different scales.
Our algorithm operates directly on points requiring no vertex connectivity information. We demonstrate and discuss the performance of our framework on a collection of point sampled 3D objects.
International conference proceedings, English - "Joyfoot's cyber system: A virtual landscape walking interface device for virtual reality applications"
S Barrera; H Takahashi; M Nakajima
2004 INTERNATIONAL CONFERENCE ON CYBERWORLDS, PROCEEDINGS, IEEE COMPUTER SOC, 286-292, 2004, Peer-reviwed, Technological limitations on current interfaces have made researches to develop new devices to interact with objects in the virtual environment. The goal of this project is to develop and build a hands-free navigation system to be integrated into virtual environments. One of the most important fields in virtual realty (VR) research, is the development of systems that allow the user to interface with the virtual environment. The most intuitive method for moving through a virtual landscape is by walking. The implementation of a walking interface for a virtual reality system also allows a greater range of biomechanical experimentation and game research. Systems ranging from different platforms have already been implemented to produce virtual walking; however these systems have been designed primarily for use with head mounted display systems. We believe that hands-free navigation, unlike the majority of navigation techniques based on hand motions, has the greatest potential for maximizing the interactivity of virtual environments, due to more direct motion of the feet. To make this possible, we created a new and simple device using acceleration sensors to detect ankle movements within the virtual environment. The acceleration sensors are attached to the foot and detect movement based on direction for three different angles. The design was called "Joyfoot's Cyber System" as shown in Figure 1. This experimentation could prove beneficial in future virtual gaming. Validation of our approach is given by discussion and illustration of some results.when they faced the front wall of Cave by first turning to the body either the right or left. We have observed that user's need time to adjust to this distorted spatial mapping, but can at least navigate in any direction after only a few minutes. However, we have not yet attempted to quantify the effect of this auto rotation technique on a user's sense of spatial relations as shown in Figure 11.
International conference proceedings, English - Toward E-appearance of human face and hair by age, expression and rejuvenation
A Bastanfard; F Takahashi; M Nakajima
2004 INTERNATIONAL CONFERENCE ON CYBERWORLDS, PROCEEDINGS, IEEE COMPUTER SOC, 306-311, 2004, Peer-reviwed, Recently, Web based facial appearance systems have received more attention by various aspects and applications like online systems. Therefore there is a request for a system to have an ability of predict and render different appearance effects on facial images for online systems. Here, an E-appearance system is proposed to predict the essential effects of facial images with different appearance. Given facial image data of the same person in two different appearance, quotient image then capture appearance characteristic of image. Then, together with warping technique we map the characteristic to any other particular persons face in order to generate new facial appearance. The technique makes experiments on different facial appearance.
International conference proceedings, English - Investigation of robust color model for edge detection on text extraction from scenery images
XH Yang; H Takahashi; M Nakajima
TENCON 2004 - 2004 IEEE REGION 10 CONFERENCE, VOLS A-D, PROCEEDINGS, IEEE, B85-B88, 2004, Peer-reviwed, This paper discusses a robust method to defect the edges of text in natural scenes, which is against the effects caused by shadow or highlight, Many color models are tested to find the robust ones under arbitrary image conditions. Moreover, some new color models, which are invariant to shadow or highlight, are proposed. By effectively utilizing color information, a simple edge threshold decision scheme is presented After that a combined scheme is introduced by virtue of the invariant characteristics of each color model in it, which could get almost intact edge information for text region. It shows good performance for the text extraction against shadow and highlight. Based on above, a simple and robust method for edge detection is achieved, which is useful for text extraction and recognition tasks.
International conference proceedings, English - A Radial Basis Function Based Approach for 3D Object Modeling and Reconstruction
Hamid Laga; Piperakis Romanos; Hiroki Takahashi; Masayuki Nakajima
The Journal of the Institute of Image Information and Television Engineers, 57, 11, 1526-1533, Nov. 2003, Peer-reviwed
Scientific journal, English - 移動可能な物体への映像投影手法
小出裕子; 橋本直己; 高橋裕樹; 中嶋正之
芸術科学会論文誌, 2, 2, 71-73, Jun. 2003, Peer-reviwed
Scientific journal, Japanese - モーションジェネレータによるバァーチャルサーカス ～リアルタイムアニメーション生成システムの試み～
野地朱真; 高橋裕樹; 中嶋正之
映情学誌, The Institute of Image Information and Television Engineers, 57, 2, 242-246, Feb. 2003, Peer-reviwed, Realistic virtual characters generated by computer graphics are increasingly required in broadcasting programs. We propose an algorithm that implements interactive, real-time motion generation for the creation of virtual acrobats that perform complex circus acrobatics using a motion generation engine to support production. To facilitate control, we designed a graphical user interface and a minimum set of inputs which give a very effective result in motion. For fast computation, we designed each character and other objects with minimum dynamics construction to perform each motion. Because a circus acrobat usually requires large space, the motion capture system cannot be used. Furthermore, traditional key-frame animation cannot apply the external forces that are important to the motion. To solve these problems, our algorithm uses dynamics simulation and is able to create a variety of motion.
Scientific journal, Japanese - A method of rendering scenes including volumetric objects using ray-volume buffers
K. Kajihara; H. Takahashi; M. Nakajima
Proceedings of Computer Graphics International Conference, CGI, IEEE Computer Society, 2003-, 230-235, 2003, We describe a rendering method that simultaneously renders both volumetric and polygonal objects. It is also possible to render volumetric objects intersected by polygonal ones or volumetric ones in the same scheme. In the proposed method, a scene including volumes and polygons overlapping each other is rendered using a ray-volume buffer that stores the colors and transmittance of a ray at each voxel. Polygons inserted in a volume are rendered by mapping the ray-volume data as 3D texture. We rendered a mixed scene of two volumes in the same scheme by considering a volume overlapping with another volume as multiple layers of translucent polygons. The ray-volume buffer method treats volumetric objects as polygons with textures. Therefore, the method can be realized using conventional graphics pipeline techniques by generating a ray volume for a 3D texture. Another feature of this method is that ray volumes can be generated without consideration of the intersection with polygons or volumes.
International conference proceedings, English - Text Image Enhancement in Scenery Images for Degraded Character Recognition
Hiroki Takahashi; Kousuke Ogata; Masayuki Nakajima
Proc. of IWAIT(International Workshop on Advanced Image Technology) 2003, 335-340, Jan. 2003
International conference proceedings, English - A Radial Basis Function Based Approach for 3D Object Modeling and Reconstruction
Hamid Laga; Piperakis Romanos; Hiroki Takahashi; Masayuki Nakajima
Proc. of IWAIT(International Workshop on Advanced Image Technology) 2003, The Institute of Electronics, Information and Communication Engineers, 102, 570, 139-144, Jan. 2003, In this paper we propose a new approach for 3D object modeling and reconstruction from range data. Our approach is based on the modelization of the object surfaces with a new set of Radial Basis Functions, we call Parametric Radial Basis Functions PRBF. First, a set of Radial Basis Functions is fitted to a set of 3D scanned points in order to reconstruct the object geometry. Our originality is the fact that the reconstruction is independent from the object geometry and the number; it can be applied for smooth objects as well as objects with sharp boundaries. To enhance the efficiency of the RBF modelization, we propose also an efficient isosurface extraction method based on volumetric processing. Unlike conventional reconstruction techniques, no prior information about the acquisition process is required. We demonstrate the efficiency of our approach through a set of experiments.
International conference proceedings, English - Image categorization using color blobs in a mobile environment
DG Ruiz; H Takahashi; M Nakajima
COMPUTER GRAPHICS FORUM, WILEY-BLACKWELL, 22, 3, 427-432, 2003, Peer-reviwed, This paper generalizes the basic idea of blobs in preattentive perception using color information. This is used as the base of a basic classification of low resolution pictures taken with mobile phones. This classification, the blob-like representation of the image and other information in user's context, such as GPS information, can be used in the presented framework as the basis of a new graphical interface for HCI (Human Computer Interaction). Similar systems whether they work with global properties of the image, which leads to inaccurate results, or with complex segmentation process that fails to capture expected objects in the scene. Most of those systems do not pay attention on other information involved in the creation of the image, such as time or location. We describe a system which uses geographical information associated with a picture in a mobile phone terminal, and with a fast segmentation based on color categorization.
Scientific journal, English - A radial basis function based approach for polygon-free reconstruction and representation of 3D objects from range data
Hamid Laga; Romanos Piperakis; Hiroki Takahashi; Masayuki Nakajima
Kyokai Joho Imeji Zasshi/Journal of the Institute of Image Information and Television Engineers, Inst. of Image Information and Television Engineers, 57, 11, 1526-1533, 2003, Peer-reviwed, The acquisition of the 3D shape of real objects is a rapidly expanding field with various applications in Computer Aided Design, archeology, design, entertainment and so on. In this paper we propose a new approach for 3D object reconstruction from range data. Our approach is based on the modelization of the object surfaces with a set of RBFs (Radial Basis Functions). Our originality is the fact that the reconstruction is independent from the object geometry
it can be applied for smooth objects as well as for objects with sharp boundaries. To enhance the efficiency of the RBF modelization, we propose also an efficient isosurfacing algorithm. Unlike conventional reconstruction techniques, no prior information about the acquisition process is required. We demonstrate the ability of our approach to reconstruct a wide range of 3D objects through a set of experiments.
Scientific journal, English - Real time detection interface for walking on CAVE
S Barrera; P Romanos; S Saito; H Takahashi; M Nakajima
COMPUTER GRAPHICS INTERNATIONAL, PROCEEDINGS, IEEE COMPUTER SOC, 105-110, 2003, Peer-reviwed, Presently, most virtual reality systems use upper body pails to interact with objects in the virtual environment. This situation is caused by technological limitations of current interface devices. Starting from this viewpoint we developed a new interface for detecting ankle motions relative to the knee. We believe that hands-free navigation, unlike the majority of navigation techniques based on hand motions, has the greatest potential for maximizing the interactivity. Of virtual environments since navigation modes are more direct motion of the feet. We Therefore, created a simple device to detect ankle movements with rotary encoders sensors. These sensors rotate according to the amount and direction of the movement of the foot. The sensors are attached to a sandal and can be used for many purposes including virtual games. Validation of our approach is given by discussion and ilustration of some experimental results.
International conference proceedings, English - A method of rendering scenes including volumetric objects using ray-volume buffers - Expanding to render scenes including overlapped volumetric objects
K Kajihara; H Takahashi; M Nakajima
COMPUTER GRAPHICS INTERNATIONAL, PROCEEDINGS, IEEE COMPUTER SOC, 230-235, 2003, Peer-reviwed, This paper describes a rendering method that simultaneously renders both volumetric and polygonal objects. It is also possible to render volumetric objects intersected by polygonal ones or volumetric ones in the same scheme. In the proposed method, a scene including volumes and polygons overlapping each other is rendered using a ray-volume buffer that stores the colors and transmittance of a ray at each voxel. Polygons inserted in a volume are rendered by mapping the ray-volume data as 3D texture. We rendered a mixed scene of two volumes in the same scheme by considering a volume overlapping with another volume as multiple layers of translucent polygons. The ray-volume buffer method treats volumetric objects as polygons with textures. Therefore, the method can be realized using conventional graphics pipeline techniques by generating a ray volume for a 3D texture. Another feature of this method is that ray volumes can be generated without consideration of the intersection with polygons or volumes.
International conference proceedings, English - 光線ボリュームバッファを用いたボリュームとポリゴン混在シーンのレンダリング方法
梶原景範; 高橋裕樹; 中嶋正之
映情学誌, The Institute of Image Information and Television Engineers, 56, 10, 1607-1612, Oct. 2002, Peer-reviwed, A rendering method that simultaneously renders both volumetric and polygonal objects is described. Using the method also makes rendering volumetric objects intersected by polygonal ones in the same scheme possible. A ray-volume buffer that stores colors and the transmittance of a ray at each voxel is described. The ray-volume buffer treats volumetric objects as textures. Therefore, the method can be achieved using conventional graphics pipeline by generating a ray-volume in advance. In contrast with the Marching Cube algorithm, the method can generate images that maintain the features of volumetric objects using a small number of surfaces because it renders a volume by using textured boundary surfaces obtained through the volumes.
Scientific journal, Japanese - 色・輪郭特徴を用いた情景画像からの文字領域抽出手法
高橋裕樹; 葛西浩一; 中嶋正之
映情学誌, 56, 6, 979-985, Jun. 2002, Peer-reviwed
Scientific journal, Japanese - Facial Age Declination Animation based on Medical Anthropometry
Azam Bastanfard; Hiroki Takahashi; Masayuki Nakajima
Proc. of NICOGRAPH Internatioanl Conference, 67-72, May 2002
International conference proceedings, English - An Interactive Action of Automatic Generating Artwork by Using an Evolutional Model
Peisuei Lee; ChiaFang Lee; Hiroki Takahashi
Proc. of IWAIT(International Workshop on Advanced Image Technology) 2002, The Institute of Electronics, Information and Communication Engineers, 101, 567, 195-198, Jan. 2002, This paper describes the process and creation of interactive computer formative system based on an evolutional model. The evolutional model has a sound environment, which has prototypes of creatures inside. Initially, the prototypes move randomly using preprogrammed "energy" within them. When the mouse is moved, these prototypes gravitate towards the cursor, which is a metaphor for the sun, the creator of life. Just as real life forms move towards the sun, so the prototypes grow and move together towards the cursor. We call these shapes "creatures." When these creatures join together, they cross over and sometimes mutate, based on the evolutional model they are following. These "creature formative system" can automatically replicate them.
International conference proceedings, English - Color image segmentation using region growing based on neighbouring region features
Hiroki Takahashi; Masayuki Nakajima
Proc. of IWAIT(International Workshop on Advanced Image Technology) 2002, The Institute of Electronics, Information and Communication Engineers, 101, 567, 97-102, Jan. 2002, Image segmentation is not only very important technique, but also challenging issue in Computer Vision. The segmentation of an image and grouping of the segmented regions as an object are very hard task for a computer, but they play a great role in human visual perception. There are, therefore, many researches in the field of color image segmentation. It is very difficult task to make a closed boundary for a region from obtained edges using edge detectors. Active contour model effectively extracts a boundary of an object, but initial boundary affects the final results. Moreover, statistical models have optimization difficulties. In this paper, a region growing approach which employs several internal features in a region and difference between two adjacent regions is proposed. Small regions occur on irregular boundaries or texture regions by using the conventional region growing segmentation approaches. Our approach reduce the small regions by using size, color distributions, edge magnitude and avcrage color of regions. Moreover, the proposed method extracts segments suitable for human visual perception. The paper shows some examples on both synthetic and real images.
International conference proceedings, English - Collision-free virtual navigation using viewpoint specific depth information
Piperakis Romanos; Hiroki Takahashi; Masayuki Nakajima
Proc. of IWAIT(International Workshop on Advanced Image Technology) 2002, The Institute of Electronics, Information and Communication Engineers, 101, 566, 39-43, Jan. 2002, Computer animation and virtual reality applications continue to gain popularity and be the focus of increasingly extensive research. However the shortcomings of a virtual environment are numerous and in order to create realistic scenes one must address a lot of practical issues. This paper presents a realistic navigation algorithm for collision free agent movement. In the scope of this paper, an agent is considered to be an autonomous, computer assisted or computer controlled entity, which unlike general collision detection and navigation algorithms relies on purely local geometric information of its surroundings to find a path towards a goal position. The approach taken is using depth information directly from the agent's view rendering pipeline to create a repelling force field around obstacles. More specifically the z-buffer of the agent's view is used to estimate a vector field around the obstacles that lie in the agent's path. By making use of the z-buffer the navigation strategy implemented is based solely on information the agent can acquire from its sensors at his present position. This makes the algorithm suitable for autonomous agents in either static or dynamic, unstructured environments, where no a priori information on the topology of the virtual world is known. Furthermore, the algorithm is simple and fast and could be easily extended to real world robots equipped with depth lenses.
International conference proceedings, English - Simulation of Human Facial Aging and Skin Senility
Azam Bastanfard; Hussein Karam Hussein; Hiroki Takahashi; Masayuki Nakajima
Proc. of IWAIT(International Workshop on Advanced Image Technology) 2002, 7-13, Jan. 2002
International conference proceedings, English - Autonomous agent motion planning in unstructured virtual world environments using Z-buffer sensor
Romanos Piperakis; Hiroki Takahashi; Masayuki Nakajima
Kyokai Joho Imeji Zasshi/Journal of the Institute of Image Information and Television Engineers, Inst. of Image Information and Television Engineers, 56, 10, 1613-1619, 2002, Peer-reviwed, Computer animation and virtual reality applications continue to gain popularity and be the focus of increasingly extensive research. However the shortcomings of a virtual environment are numerous anal in order to create realistic scenes one must address a lot of practical issues. This paper deals with a realistic navigation strategy for collision free agent movement. In the scope of this paper, an agent is considered to be an autonomous, computer assisted or computer controlled entity, which unlike general collision detection and navigation algorithms relies on purely local geometric information of its surroundings to find a path towards a goal position. The approach taken is using depth information directly from the agent's view rendering pipeline to create a repelling force field around obstacles. More specifically the z-buffer of the agent's view is used to estimate a vector field around the obstacles that lie in the agent's path. By making use of the z-buffer the navigation strategy implemented is based solely on information the agent can acquire from its sensors at his present position. This makes the algorithm suitable for autonomous agents in either static or dynamic, unstructured environments, where no a priori information on the topology of the virtual world is known. Furthermore, the algorithm is simple and fast and could be easily extended to real world robots equipped with depth lenses.
Scientific journal, English - Animation Synthesis of Virtual Fish using Motion Extraction from Video
Hiroki Takahashi; Junji Hatoya; Masayuki Nakajima
The Journal of the Institute of Image Information and Television Engineers, 55, 5, 725-732, May 2001, Peer-reviwed
Scientific journal, English - A study on view-dependent line rendering
Youngha Chang; Suguru Saito; Hiroki Takahashi; Masayuki Nakajima
Proc. of IWAIT(International Workshop on Advanced Image Technology) 2001, 229-234, Feb. 2001
International conference proceedings, English - Extraction of text regions from scenery images using multiple features
Hiroki Takahashi; Kouichi Kasai; Daewoo Kim; Masayuki Nakajima
Proc. of IWAIT(International Workshop on Advanced Image Technology) 2001, 97-102, Feb. 2001
International conference proceedings, English - Graph-based color image segmentation using edge magnitude for image understanding
Hiroki Takahashi; Masayuki Nakajima
Proc. of IWAIT(International Workshop on Advanced Image Technology) 2001, 93-96, Feb. 2001
International conference proceedings, English - Animation Synthesis for Virtual Fish from Video
Hiroki Takahashi; Junji Hatoya; Naoki Hashimoto; Masayuki Nakajima
Proc. of the 10th ICAT(International Conference on Artificial reality and Telexistence), 90-97, Oct. 2000, Peer-reviwed
International conference proceedings, English - Waraji: 仮想環境のための足を用いた入力インターフェース
増野智経; 齋藤豪; 高橋裕樹; 中嶋正之
映情学誌, The Institute of Image Information and Television Engineers, 54, 6, 833-839, Jun. 2000, Peer-reviwed, Various types of interface devices operated with the hands have been developed and are widely used. However, we use our legs for walking in the real world, so it is natural to use an interface devices operated with the legs for moving around a virtual environment. In this paper, we have developed a new interface device "Waraji (WAlking, Running, And Jumping Interface)". Using Waraji, users can work at ease in a virtual environment because their hands are free from movement operations. In addition, because Waraji is smaller than other interfaces for movement, it can he easily worn. Experiments have shown that Waraji provides operationality similar to that of a joystick. It will be useful for surround-display virtual-environment systems such as CAVE (CAVE Automatic Virtual Environment).
Scientific journal, Japanese - Creating virtual environment based on video data with forward motion
XH Zhang; H Takahashi; M Nakajima
IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS, IEICE-INST ELECTRONICS INFORMATION COMMUNICATIONS ENG, E83D, 4, 931-936, Apr. 2000, Peer-reviwed, The construction of photo-realistic 3D scenes from video data is an active and competitive area of research in the fields of computer vision, image processing and computer graphics. In this paper we address our recent work in this area. Unlike most methods of 3D scene construction, we consider the generation of virtual environments from video sequence with a video-cam's forward motion. Each frame is decomposed into sub-images, which are registered correspondingly using the Levenberg-Marquardt iterative algorithm to estimate motion parameters. The registered sub-images are correspondingly pasted together to form a pseudo-3D space. By controlling the position and direction, the virtual camera can walk through this virtual space to generate novel 2D views to acquire an immersive impression. Even if the virtual camera goes deep into this virtual environment, it can still obtain a novel view while maintaining relatively high resolution.
Scientific journal, English - A Framework for 2D Image-Based Visual Stereo Image Generation
Zhang Xiaohua; Hiroki Takahashi; Masayuki Nakajima
Proc. of IWAIT(International Workshop on Advanced Image Technology) 2000, The Institute of Image Information and Television Engineers, 24, 2, 177-182, Jan. 2000, The rapid expansion of multimedia techniques has made stereo display systems more prevalent than ever. Due to the insufficiency of stereo sources, we propose a framework for generating visual stereo image pairs based on the common 2D images. The framework consists of two parts: rendering method by exploiting the pseudo 3D structure and synthesis method by exploiting the motion information between image frames. The tentative experimental results illustrates that these approaches can help viewer to perceive and understand the three-dimensionality of the world.
International conference proceedings, English - Evolutional design and training algorithm for feedforward neural networks
H Takahashi; M Nakajima
IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS, IEICE-INST ELECTRONICS INFORMATION COMMUNICATIONS ENG, E82D, 10, 1384-1392, Oct. 1999, Peer-reviwed, Tn pattern recognition using neural networks, it is very difficult for researchers or users to design optimal neural network architecture for a specific task. It is possible far any kinds of neural network architectures to obtain a certain measure of recognition ratio. It is, however, difficult to get an optimal neural network architecture for a specific task analytically in the recognition ratio and effectiveness of training. In this paper, an evolutional method of training and designing feedforward neural networks is proposed. In the proposed method, a neural network is defined as one individual and neural networks whose architectures are same as one species. These networks are evaluated by normalized M.S.E.(Mean Square Error) which presents a performance of a network for training patterns, Then, their architectures evolve according to an evolution rule proposed here. Architectures of neural networks, in other words, species, are evaluated by another measurement of criteria compared with the criteria of individuals. The criteria assess the most superior individual in the species and the speed of evolution of the species. The species are increased or decreased in population size according to the criteria. The evolution rule generates a little bit different architectures of neural network from superior species. The proposed method, therefore, can generate variety of architectures of neural networks. The designing and training neural networks which performs simple 3 x 3 and 4 x 4 pixels which include vertical, horizontal and oblique. lines classifications and Handwritten KATAKANA recognitions are presented. The efficiency of proposed method is also discussed.
Scientific journal, English - 大型VR システムのための能動型3次元位置センサAMUSE
鈴木尚亨; 高橋裕樹; 中嶋正之
日本VR学会誌, THE VIRTUAL REALITY SOCIETY OF JAPAN, 4, 3, 511-520, Sep. 1999, Peer-reviwed, In this paper, a wireless and lightweight interface A-MUSE(Active emission tracking system in MUltiscreen Environment), which makes it possible to use without preventing users' illusion of immersion in large-scale VR(Virtual Reality) systems such as CAVE(CAVE Automatic Virtual Environment), is proposed. A-MUSE measures 6DOF(degrees of freedom) which are position and direction of the device. It projects five pairs of rays onto screens and then it measures 6DOF from geometrical relation between the initial and the transmitted state. It also possible to use several devices simultaneously. By using projective transformation invariants of five pairs of rays, A-MUSE makes a correspondence of rays between the initial and transmitted state. The correspondence process includes two steps. One is to detect a pair of rays projected from one device among a large number of rays. The other is to correspond each ray in the initial state to a ray in the pair of transmitted rays. The computational complexity of the process is n^5 order of the number of devices. Therefore, acceleration of the process is proposed by setting some restrictions to the process. Moreover, error reduction method is proposed for the practical use of A-MUSE in order to reduce the error occurred from several factors. It gives restriction to a matrix used for measuring of 6DOF. Finally, in order to evaluate the proposed system, A-MUSE is compared with the alternating current magnetic sensor which is usually used in CAVE. The measuring results of A-MUSE is more precise than that of magnetic sensor.
Scientific journal, Japanese - The Calibration of Camera Using Projective Invariance for Virtual Studio
Seowon Han; Joonwhaon Lee; Hiroki Takahashi; Masayuki Nakajima
The Journal of the Institute of Image Information and Television Engineers, The Institute of Image Information and Television Engineers, 53, 3, 417-422, Mar. 1999, Peer-reviwed, Chromakey method is one of key technologies for realizing virtual studio, and the blue portions of a captured image in virtual studio, are replaced with a computer generated or real image. The replaced image must be changed according to the camera parameter of studio for natural merging with the non-blue portions of a captured image. This paper proposes a novel method to extract camera parameters using the recognition of pentagonal patterns that are painted on a blue screen. We extract corresponding points between a blue screen and a captured image using the projective invariant features of a pentagon. Then, calculate camera parameters using corresponding points by the modification of Tsai's method. Experimental results indicate that the proposed method is more accurate compared to conventional method and can process about twelve frames of video per a second in Pentium-MMX processor with CPU clock of 166MHz.
Scientific journal, English - Construction of virtual environment from video data with forward motion
XH Zhang; H Takahashi; M Nakajima
ADVANCED MULTIMEDIA CONTENT PROCESSING, SPRINGER-VERLAG BERLIN, 1554, 301-312, 1999, Peer-reviwed, The construction of photo-realistic 3D scenes from video data is an active and competitive area of research in the fields of computer vision, image processing and computer graphics. In this paper we address our recent work in this area. Unlike most methods of 3D scene construction, we consider the generation of virtual environments from video sequences with a video-cam's forward motion. Each frame is decomposed into sub-images, which are registered correspondingly using the Levenberg-Marquardt iterative algorithm to estimate motion parameters. The registered sub-images are correspondingly pasted together to form a pseudo-3D space. By controlling the position and direction, the virtual camera can walk through this virtual space to create novel 2D views to acquire an immersive impression. Even if the virtual camera goes deep into this virtual environment, it can still obtain a novel view while maintaining high resolution.
Scientific journal, English - Interaction Using Speech and a Virtual Stich in a CAVE
Kanzan Fujishiro; Hiroki Takahashi; Masayuki Nakajima
Proc. of IWAIT(International Workshop on Advanced Image Technology) 1999, 207-212, Jan. 1999
International conference proceedings, English - Design and Manipulation of 3-D geometry using a CAVE System
Naoki Hashimoto; Hiroki Takahashi; Masayuki Nakajima
Proc. of IWAIT(International Workshop on Advanced Image Technology) 1999, 201-206, Jan. 1999
International conference proceedings, English - Camera Calibration for Virtual Studio using Projective Invariance
Seowon Han; Hiroki Takahashi; Joonwhaon Lee; Masayuki Nakajima
Proc. of the 8th ICAT(International Conference on Artificial reality and Telexistence), 202-207, Dec. 1998, Peer-reviwed
International conference proceedings, English - Generation of 3d hair model from hair volume
WM Kong; H Takahashi; M Nakajima
MULITMEDIA NETWORKS: SECURITY, DISPLAYS, TERMINALS, AND GATEWAYS, SPIE-INT SOC OPTICAL ENGINEERING, 3228, 211-218, 1998, This paper proposes a hair volume algorithm that is effective in producing realistic hair model for individual. The hair volume is produced from three images of the head taken from the right, back and top view. This hair volume represents the real space volume where hairs are found and guides the hair strands to move in the desired direction. Hair strands are randomly generated on the skull. The outline region acquired through image processing together with the hair volume ensures that the randomly generated hair strands fall neatly into the hair volume to produce hair model resembling the input images. in the generation of synthetic humans and creatures in movies, This hair model can find many applications multimedia and computer game productions.
International conference proceedings, English - Two dimensional shape blending based on centroid of mass
Zhang Xiaohua; Hiroki Takahashi; Masayuki Nakajima
Kyokai Joho Imeji Zasshi/Journal of the Institute of Image Information and Television Engineers, Inst. of Image Information and Television Engineers, 52, 7, 1062-1064, 1998, Peer-reviwed, In this paper we proposed a method for two dimension polygonal shape blending. The original Cartesian coordinates representation of polygon are converted to a new representation based on centroid, which can efficiently express the relations between vertices when blending two key polygons. In order to improve the results of blending, polygons are correspondingly decomposited into several sub-polygons. Main frame is formed by connecting orderly the centroids of each sub-polygon. Therefore, interpolations of main frame polygons and sub-polygons can reflect the overall interpolation in detail. Tests suggest that it work well enough and more smooth for most of realistic cases.
Scientific journal, English - A classification algorithm of 3D volumetric data for hierarchical visualization
M Sato; Y Liu; H Takahashi; M Nakajima
INPUT/OUTPUT AND IMAGING TECHNOLOGIES, SPIE-INT SOC OPTICAL ENGINEERING, 3422, 168-175, 1998, This paper presents one part of our work on "hierarchical visualization." Here, we propose an efficient hierarchical structure for the visualization of 3D volumetric data, where for instance, data compression techniques are embedded into the hierarchical structure. The hierarchical structure consists of two layers. The first hierarchy roughly visualizes the whole lossy compressed data so that we can quickly understand and interpret the outline of the whole 3D volumetric dataset. This step allows users to choose the desired parts of the 3D volumetric data. The second hierarchy is used for scrutinizing the detail of the chosen parts using lossless compressed data.
To implement the hierarchical structure we propose a partitioning algorithm for 3D volumetric data based on principal component analysis. With principal component analysis, the original 3D volumetric space can be divided into a number of 3D volumetric blocks such that each block contains similar data. Analyzing these specific blocks and taking advantage of an octree hierarchy, from the whole 3D volumetric dataset we can easily access only the parts which are required for display. The proposed partitioning algorithm should be very useful in reducing the amount of rendering, which means that we will need only to precisely render the blocks required for display, and not the whole 3D volumetric dataset.
International conference proceedings, English - Generating Intelligent Behavior for artificial creatures searching for their mates by using pheromones
Peisuei Lee; Hiroki Takahashi; Masayuki Nakajima
An Asia Pacific symposium on Optoelectronics, Proceedings of SPIE, 34, Vol.3422, No.25, pp.210-217, 1998
International conference proceedings, English - Generation of virtual fish movement from video
J Hatoya; M Nakajima; H Takahashi
VSMM98: FUTUREFUSION - APPLICATION REALITIES FOR THE VIRTUAL AGE, VOLS 1 AND 2, I O S PRESS, 122-127, 1998, Peer-reviwed, Creating natural mo movement for virtual creatures is very difficult. if possible, we would like to base the movement of artificial creatures on the movement of real creatures. Therefore this paper shoes a way to extract a real creature's movement from,ideo. Our target creature is a fish. We propose a method to drive a virtual fish using a real fish's movement. Ln order to extract the fish's movement, the fish region is first extracted from the video. The three-dimensional (3D) position and posture of the fish are then obtained by object matching. Finally, an animation of the natural-looking movement of the virtual fish is made using these parameters.
International conference proceedings, English - 多様性のある人工生物の自動形成のための進化的モデリング
Peisuei Lee; Hiroki Takahashi; Masayuki Nakajima; Takeshi Agui
The Journal of the Institute of Image Information and Television Engineers, 51, 8, 1284-1290, Nov. 1997, Peer-reviwed
Scientific journal, Japanese - Hair image generating algorithm using Fractional hair model
Masayuki Nakajima; Seiichi Saruta; Hiroki Takahashi
Signal Processing: Image Communication, 9, 267-273, Sep. 1997, Peer-reviwed
Scientific journal, English - Multi-Screen Virtual Reality System: VROOM --Hi-Resolution and four-screen Stereo Image Projection System--
Masayuki Nakajima; Hiroki Takahashi
Proc. of IWAIT(InternationalWorkshop on Advanced Image Technology) 1997, 95-100, Jan. 1997
International conference proceedings, English - Semi-automatic feature specification based on snakes for image morphing
AE Hassanien; H Takahashi; M Nakajima
APPLICATIONS OF DIGITAL IMAGE PROCESSING XX, SPIE - INT SOC OPTICAL ENGINEERING, 3164, 494-502, 1997, Recent efforts in image morphing research aim at improving both user interface and warping results. To specify feature points in two images, the user interface takes up much time and it allows the warping specification by the user which represents very tedious work. In this paper, we propose a semi-automatic algorithm based on active contour model (snake) to specify the feature correspondence between two given images. It allows a user to extract a contour that defines a facial features such as Lips, mouth, profile, etc., by specifying only endpoints of the contour around the feature that serve as the extremities of a contour. The proposal algorithm uses these two points as anchor points, and automatically computes the image information around these endpoints to provide boundary conditions. Then we optimize the contour by taking this information into account close to its extremities. During the iterative optimization process, the image forces are moving progressively from the contours extremities towards its center to define the feature. Once the feature correspondence points are paired, the intermediate images are generated by interpolating the positions of feature points linearly. The proposal algorithm helps the user to define easily the exact position of a feature. It may also reduce the time taken to establish feature correspondence between two images.
International conference proceedings, English - Database Guided Realistic Grasping Posture Generation for Virtual Actors
Yahya Aydin; Hiroki Takahashi; Masayuki Nakajima
PCS'97, 665-670, 1997, Peer-reviwed
International conference proceedings, English - Generation of 3D Hair Model from Multiple Pictures
Kong Wai Ming; Hiroki Takahashi; Masayuki Nakajima
Multimedia Modeling'97, 183-196, 1997, Peer-reviwed
International conference proceedings, English - Database Guided Animation of Grasp Movement for Virtual Actors
Yahya Aydin; Hiroki Takahashi; Masayuki Nakajima
Multimedia Modeling'97, 213-226, 1997, Peer-reviwed
International conference proceedings, English - 遺伝的アルゴリズムを用いた最適な階層型神経回路網の構造決定に関する一考察
Hiroki Takahashi; Masayuki Nakajima
The IEICE Transactions on Information and Systems, J79-D-II, 11, 1920-1928, Nov. 1996, Peer-reviwed
Scientific journal, Japanese - Arm-Posture Creation Based on Iso-Comfort Regions
Yahya Aydin; Hiroki Takahashi; Masayuki Nakajima
The Journal of the Institute of Image Information and Television Engineers, 50, 5, 586-593, May 1996, Peer-reviwed
Scientific journal, English - Compression of animation using 3D structure runlength coding
Yu Liu; Hiroki Takahashi; Masayuki Nakajima
Terebijon Gakkaishi, Inst of Television Engineers of Japan, 50, 6, 761-767, 1996, Peer-reviwed, Computer animation is typical of artificial image sequences different from video images. Video compression standards are not well suitable for the artificial images. In order to efficiently compress animation, this paper introduces a novel concept 'three-dimensional structure runlength coding' (briefly 3D SRC), which is based on the two-dimensional structure runlength coding (briefly 2D SRC). The paper presents a basic algorithm of 3D SRC which is expanded simply from 2D SRC. In 3D SRC, the key technique is to compare each pixel of the current frame with its three-dimensional neighbors - a pixel of the previous frame and neighboring pixels of the current frame. The results of the comparison are compressed by runlength coding. Our experimental results show that in compression of animation, the data compressed by 3D SRC become one-third of the data compressed by 2D SRC on average.
Scientific journal, English - Semi-automatic 3D Virtual Fish Modeling based on 2D Texture
Masayuki Nakajima; Hisaya Hagiwara; Kong Wai Ming; Hiroki Takahashi
Proceedings International Workshop on New Video Media Technology, 18-21, 1996
International conference proceedings, English - Designing and Learning Algorithm of Neural Networks for Pattern Recognition
Hiroki Takahashi; Masayuki Nakajima
Proceedings IWISP'96, 497-500, 1996, Peer-reviwed
International conference proceedings, English - Generation of 3D hair model from 2D image using image processing
WM Kong; H Takahashi; M Nakajima
APPLICATIONS OF DIGITAL IMAGE PROCESSING XIX, SPIE - INT SOC OPTICAL ENGINEERING, 2847, 303-311, 1996, In the field of human animation; hair represents one of the most challenging problem and therefore has been one of the least satisfactory aspects of human images rendered to date. This paper proposes a method to generate realistic hair model for individuals based on image processing. The analysis and recognition of hair strands by image processing provides valuable data, particularly hair outline and the now direction of the hair for the rendering of realistic hair model for individuals. The image is binarised prior to lines extraction and the hair region is determined by a series of expansion and contraction. These data provide the basic guidance for the generation of the hair model. A simplified spring model is used for the hair modeling. In this spring system a strand of hair is modeled as a series of interconnected masses, springs and hinges. Hair strands are randomly generated on the skull. The outline region acquired through image processing ensures that the randomly generated bait strands fall neatly into the hair region. These strands are randomly rotated to shuffle the hair strands. In the case of hair strands falling out of the outline region, weights are added or reduced at the interconnected masses in order to move the strand back into the hair region. The lines extracted by image processing serves as guide-lines directing the hair strands to point in the desired direction. This realistic hair model can find many applications in the generation of synthetic humans and creatures in movies, multimedia and computer game productions.
International conference proceedings, English - MIMD分散並列計算機に適したレイトレーシングの並列化アルゴリズムの検討
Masayuki Nakajima; Masami Mizutani; Hiroki Takahashi
The Journal of the Institute of Image Information and Television Engineers, 49, 10, 1272-1279, Oct. 1995, Peer-reviwed
Scientific journal, Japanese - Realistic Hand-Posture Generation Using Octree Data Structure
Yahya Aydin; Hiroki Takahashi; Masayuki Nakajima
Asia Display'95,Proceedings of the 15th International Display Research Conference, 403-406, 1995, Peer-reviwed
International conference proceedings, English - Parallel Volume Rendering on Massive Parallel Computer
Masayuki Nakajima; Masami Mizutani; Hiroki Takahashi
Asia Display'95,Proceedings of the 15th International Display Research Conference, 901-904, 1995, Peer-reviwed
International conference proceedings, English - A Study On CG Image Coding Using Structure Runlength At Low Bit Rates
Yu Liu; Hiroki Takahashi; Zheng Zhong; Masayuki Nakajima
VLBV95, D-2, 1995, Peer-reviwed
International conference proceedings, English - Designing and Learning Feedforward Neural Networks using a Structure Evolution Rule
Hiroki Takahashi; Masayuki Nakajima
Conference Proceedings DICTA-95, 625-630, 1995
International conference proceedings, English - Realistic Arm-Posture Creation Based on Iso-Comfort Regions
Yahya Aydin; Hiroki Takahashi; Masayuki Nakajima
ACCV'95, Proceedings 2, 245-248, 1995, Peer-reviwed
International conference proceedings, English - Hair Image Generating Algorithm Using Fractional Hair Model
Masayuki Nakajima; Seiichi Saruta; Hiroki Takahashi
6th ICECGDG, 668-672, Aug. 1994, Peer-reviwed
International conference proceedings, English - A Study on Detecting Finger Motion to Realize a Virtual World
Masayuki Nakajima; Hirokuni Shiba; Hiroki Takahashi
6th ICECGDG, The Institute of Image Information and Television Engineers, 17, 42, 732-736, Aug. 1994, Peer-reviwed, In recent years there are studies to input the data of a hand motion in itself as a new Man-Machine Interface to realize a virtual world. Especially, the motion detection method without wearing input sensors, using only an image processing engine, is recognized as effective one, so a large number of studies have been proposed on this method. We are concerned with a finger motion. The study proposed in this paper to detect a finger motion in real time and interactively. The subjects of this paper are as follows. At first, we mark a base and tip of finger with a color tape to make easy a process to detect the coordinates of a finger in a space of 3-dimension in real time. Next, we make a finger flame model and a decision rule of a finger shape in a computer to make a finger model on display with minimum data. Lastly, we discuss the model maching method to move a model made in a computer in time to a finger motion in physical space.
International conference proceedings, English - Designing neural networks using several kinds of activation functions by genetic algorithms
Hiroki Takahashi; Takeshi Agui; Hiroshi Nagahashi
3rd International Conference on computer graphics and image processing GKPO'94, 393-402, 1994
International conference proceedings, English - DESIGNING ADAPTIVE NEURAL-NETWORK ARCHITECTURES AND THEIR LEARNING PARAMETERS USING GENETIC ALGORITHMS
H TAKAHASHI; T AGUI; H NAGAHASHI
SCIENCE OF ARTIFICIAL NEURAL NETWORKS II, SPIE - INT SOC OPTICAL ENGINEERING, 1966, 208-215, 1993
International conference proceedings, English - RECOGNITION OF HANDWRITTEN KATAKANA IN A FRAME USING MOMENT INVARIANTS BASED ON NEURAL NETWORK
T AGUI; H TAKAHASHI; M NAKAJIMA; H NAGAHASHI
VISUAL COMMUNICATIONS AND IMAGE PROCESSING 91 : IMAGE PROCESSING, PTS 1 AND 2, SPIE - INT SOC OPTICAL ENGINEERING, 1606, 188-197, 1991
International conference proceedings, English - RECOGNITION OF HANDWRITTEN KATAKANA IN A FRAME USING MOMENT INVARIANTS BASED ON NEURAL NETWORK
T AGUI; H TAKAHASHI; M NAKAJIMA; H NAGAHASHI
VISUAL COMMUNICATIONS AND IMAGE PROCESSING 91 : IMAGE PROCESSING, PTS 1 AND 2, SPIE - INT SOC OPTICAL ENGINEERING, 1606, 188-197, 1991, Peer-reviwed
International conference proceedings, English
MISC
- Halftone Representation with Circular Cutting Pattern for Choshi Design System
Natsuki Takayama; Hiroki Takahashi
彫紙と呼ばれる立体造形の制作支援を行う手法が提案されているが，下絵画像の作製過程で違和感のある疑似輪郭が生成される場合がある．そこで，このような疑似輪郭の緩和に必要な階調数を得るための，切削パターンを用いた疑似階調表現手法について検討する．, The Institute of Image Information and Television Engineers, Nov. 2014, The Journal of The Institute of Image Information and Television Engineering, 68, 11, 525-527, Japanese, Peer-reviwed, Report scientific journal, 1342-6907, 130004700488 - Genetic Algorithm
Hiroki Takahashi
Feb. 2012, 映情学誌, 66, 3, 209-211, Japanese, Introduction other - Processing
Hiroki Takahashi
Inst. of Image Information and Television Engineers, 2010, Kyokai Joho Imeji Zasshi/Journal of the Institute of Image Information and Television Engineers, 64, 12, 1841-1849, Japanese, Introduction other, 1342-6907, 79952156480 - 3D model databases and tools
Hamid Laga; Hiroki Takahashi
Inst. of Image Information and Television Engineers, 2009, Kyokai Joho Imeji Zasshi/Journal of the Institute of Image Information and Television Engineers, 63, 2, 194-198, Japanese, Introduction other, 1342-6907, 63849145752 - Cuda (computer unified device architechture)
Hamid Laga; Hiroki Takahashi
Inst. of Image Information and Television Engineers, 2009, Kyokai Joho Imeji Zasshi/Journal of the Institute of Image Information and Television Engineers, 63, 4, 465-470, Japanese, Introduction other, 1342-6907, 67650072920 - Cell
Hiroki Takahashi
Inst. of Image Information and Television Engineers, 2008, Kyokai Joho Imeji Zasshi/Journal of the Institute of Image Information and Television Engineers, 62, 1, 45-47, Japanese, Introduction other, 1342-6907, 40449139368 - NICOGRAPH2006年度活動総括
高橋裕樹
Jul. 2007, 芸術科学会誌DiVA(Digital, Interactive and Visual Art), 11, 133-136, Japanese, Introduction other - 第2回デジタルミュージック・コンテスト開催報告
西原清一; 大村哲弥; 石原尚; 片岸一起; 石川智治; 高橋裕樹
Jul. 2007, 芸術科学会誌DiVA(Digital, Interactive and Visual Art), 11, 144-151, Japanese, Introduction other - 顔情報処理技術
高橋裕樹
人間が視覚を通して顔から得る情報は,対象となる人物が誰であるのかという個人を識別する情報とともに,性別,年齢,人柄の印象などの人物に関する属性や,感情,意図,関心などの心理状態など多様である.このような顔が伝える情報の処理をコンピュータで実現することは,セキュリティシステムからエンタテインメント分野まで広範囲な応用が可能であり,現在,研究が盛んに行われている.本稿では,「顔」を対象とした情報処理システムを多角的な方面から俯瞰し,その技術を概観する., The Institute of Image Information and Television Engineers, Apr. 2007, 映情学誌, 61, 4, 447-452, Japanese, Introduction other, 1342-6907, 110006854572, AN10588970 - 第19回NICOGRAPH論文コンテスト開催報告
高橋裕樹
夏目書房, Apr. 2004, 芸術科学会誌DiVA(Digital, Interactive and Visual Art), 6, 6, 68-81, Japanese, Introduction other, 40015164575, AA11926363 - 研究室に行ってみた!! 第6回 東京工業大学 精密機械工学研究所 佐藤・小池研究室
高橋裕樹
夏目書房, Apr. 2004, 芸術科学会誌DiVA(Digital, Interactive and Visual Art), 6, 6, 106-109, Japanese, Introduction other, 40015164580, AA11926363 - SIGGRAPH'03報告 --論文概要--
高橋裕樹
Mar. 2004, 芸術科学会論文誌, 3, 1, 45-68, Japanese, Peer-reviwed, Introduction other - パナソニックセンター
高橋裕樹; 青木里枝; 田中紀成; 船津聡
The Institute of Image Information and Television Engineers, Jul. 2003, 映情学誌, 57, 7, 802-805, Japanese, Introduction other, 1342-6907, 110003671155, AN10588970 - CGアニメーション
高橋裕樹
The Institute of Image Information and Television Engineers, Apr. 2003, 映情学誌, 57, 4, 440-441, Japanese, Introduction other, 1342-6907, 110003671128, AN10588970 - SIGGRAPH'2002報告 --論文概要--
高橋裕樹
Dec. 2002, 芸術科学会論文誌, 1, 4, 182-199, Japanese, Peer-reviwed, Introduction other, 10011700842 - 東京女子医科大学大学院先端生命医科学研究所・ME 連携ラボインテリジェントオペ室
高橋裕樹; 油井慶康; 小西陽平; 坂口崇裕; 山口晃弘
The Institute of Image Information and Television Engineers, Dec. 2002, 映情学誌, 56, 12, 1928-1932, Japanese, Introduction other, 1342-6907, 110003691110, AN10588970 - SIGGRAPH2001 論文概要
高橋裕樹; 橋本直己
Nov. 2001, 第17回NICOGRAPH論文コンテスト論文集, 245-252, Japanese, Introduction other, 10011700841 - CAVE システムの動向
高橋裕樹; 中嶋正之
Jan. 2000, 月刊ディスプレイ, 6, 1, 76-79, Japanese, Introduction other - CG(Computer Graphics)分野におけるモデリング手法 --現実感の高いCG 映像の生成をめざして--
高橋裕樹; 中嶋正之
1999, 計算工学, 4, 2, 66-71, Japanese, Introduction other, 1341-7622, 10012149241, AA11206149 - 仮想現実世界構築のための指の動きの検出法
中嶋正之; 高橋裕樹
1995, 画像ラボ(日本工業出版), 6, 3, 20-24, Japanese, Introduction other
Books and other publications
Lectures, oral presentations, etc.
- 個人差を考慮した色補正のための色覚推定
海林 拓磨; 高橋 裕樹
Oral presentation, Japanese, 映情学技報
20 Feb. 2024
19 Feb. 2024- 20 Feb. 2024 - 領域代表色クラスタリングに基づくフォトタイルモザイク生成
永山 寛人; 高橋 裕樹
Oral presentation, Japanese, 映情学技報
19 Feb. 2024
19 Feb. 2024- 20 Feb. 2024 - Explainable Deep Clustering for Wafer Defect Pattern Classification
Yuki Okazaki; Hiroki Takahashi
Oral presentation, Japanese, 信学技法
03 Mar. 2023
02 Mar. 2023- 03 Mar. 2023 - 3次元構図解析に基づく不動産居室の撮影支援
Taiki Akama; Hiroki Takahashi
Oral presentation, Japanese, 動的画像処理実利用可ワークショップ2022, Domestic conference
03 Mar. 2022 - 指先皮膚特徴解析による手足症候群の早期発見支援
Yuya Honda; Hiroki Takahashi
Oral presentation, Japanese, The Institute of Image Electronics Engineers of Japan, Domestic conference
27 Feb. 2022 - Tongue Diagnosis Support Based on Tongue Coating Features Analysis
Biao Li; Hiroki Takahashi
Oral presentation, English, The Institute of Image Electronics Engineers of Japan, Domestic conference
27 Feb. 2022 - 3D Light Source Direction Estimation from Single Image Using Known Objects for Augmented Reality
Yusuke Mukai; Hiroki Takahashi
Oral presentation, Japanese, ITE Technical Report, Domestic conference
21 Feb. 2022 - Spatial Temporal Graph Convolution-Transformer に基づく手話認識の検討
Natsuki Takayama; Hiroki Takahashi
Oral presentation, Japanese, 動的画像処理実利用可ワークショップ2021, Domestic conference
04 Mar. 2021 - 手話の複合語認識のための単語間動作特徴補間を用いたデータ拡張
Natsuki Takayama; Hiroki Takahashi
Poster presentation, Japanese, 23rd Meeting on Image Recognition and Understanding, Domestic conference
03 Aug. 2020 - 3D Light Source Direction Estimation from Single Image Using Cylinder for Augmented Reality
Yusuke Mukai; Hiroki Takahashi
Oral presentation, Japanese, ITE Technical Report, Domestic conference
13 Mar. 2020 - 衣服形状特徴を用いたインタラクティブな衣服の折り畳み手順呈示
Megumi Kido; Hiroki Takahashi
Oral presentation, Japanese, 動的画像処理実利用可ワークショップ2020, Domestic conference
09 Mar. 2020 - TCNとストローク特性に基づいたバドミントン得失点要因解析
Yosuke Kinoshita; Hiroki Takahashi
Oral presentation, Japanese, 動的画像処理実利用可ワークショップ2020, Domestic conference
09 Mar. 2020 - Generation of hiragana Ambigram Based on Character Structure Characteristics
Kazuki Inoue; Hiroki Takahashi
Oral presentation, Japanese, ITE Technical Report, Domestic conference
27 Feb. 2020 - Composition Presentation of Room Images with Composition Features
Taiki Akama; Masachika Suzuki; Hisao Kimura; Yoshio Asada; Keisuke Suzuki; Hiroki Takahashi
Oral presentation, Japanese, ITE Technical Report, Domestic conference
27 Feb. 2020 - Stroke Classification for Badminton Game Based on TCN and Stroke Characteristic
Yosuke Kinoshita; Hiroki Takahashi
Oral presentation, Japanese, ITE Winter Annual Convention 2019, Domestic conference
12 Dec. 2019 - Tongue Coating Region Extraction Based on Color Analysis for Tongue Diagnosis Support
Ryusuke Ito; Hiroki Takahashi; Kiyohide Tomoka
Oral presentation, Japanese, ITE Winter Annual Convention 2019, Domestic conference
12 Dec. 2019 - Photography Support with Composition Features of One Vanishing Point Room Images
Taiki Akama; Masachika Suzuki; Hisao Kimura; Yoshio Asada; Hiroki Takahashi
Oral presentation, Japanese, ITE Winter Annual Convention 2019, Domestic conference
12 Dec. 2019 - Fold Guide Position Presentation Using Clothing Shape Feature
Megumi Kido; Hiroki Takahashi
Oral presentation, Japanese, ITE Winter Annual Convention 2019, Domestic conference
12 Dec. 2019 - Hiragana Ambigram Structure Generation
Kazuki Inoue; Hiroki Takahashi
Oral presentation, Japanese, ITE Winter Annual Convention 2019, Domestic conference
12 Dec. 2019 - ひらがなアンビグラム生成手法の検討
Kazuki Inoue; Hiroki Takahashi
Oral presentation, Japanese, Visual Computing Workshop 2019, The journal of the Institute of Image Electronics Engineers of Japan : visual computing, devices & communications, Domestic conference
01 Dec. 2019 - Stroke Analysis for Badminton Game Based on TCN and Stroke Characteristics
Yosuke Kinoshita; Hiroki Takahashi
Oral presentation, Japanese, 映情学技報, Domestic conference
14 Nov. 2019 - 焦点距離の異なる画像対からのブラー差分特徴に基づく2段階自動フォーカルブラー領域分割の検討
Natsuki Takayama; Hiroki Takahashi
Poster presentation, Japanese, 22nd Meeting on Image Recognition and Understanding, Domestic conference
29 Jul. 2019 - Recommendation for Rental House based on Personal Preference
Cao Yang; Shinichi Nunoya; Yusuke Suzuki; Masachika Suzuki; Yoshio Asada; Hiroki Takahashi
Oral presentation, English, 信学技報, Domestic conference
14 Mar. 2019 - 3D Reconstruction from Segments in Textureless Environment
Zhengnan Yu; Hiroki Takahashi
Oral presentation, English, 信学技報, Domestic conference
14 Mar. 2019 - Kansei Retrieval of Real Estate Properties
Naoko Kobayashi; Shinichi Nunoya; Yusuke Suzuki; Masachika Suzuki; Yoshio Asada; Hiroki Takahashi
Oral presentation, Japanese, 信学技報, Domestic conference
14 Mar. 2019 - Annotation Assistant using Words Recognition for Building Japanese Sign Language Corpus
Yuka Nanboku; Hiroki Takahashi
Oral presentation, Japanese, ITE Technical Report, Domestic conference
12 Mar. 2019 - 手話翻訳と音声認識に基づく手話-音声相互対話システムの検討
Natsuki Takayama; Hiroyuki Hayashi; Shota Inoue; Akira Utsumi; Hiroki Takahashi
Oral presentation, Japanese, 動的画像処理実利用可ワークショップ2019, Domestic conference
09 Mar. 2019 - Gait Identification Using 3D Pose Estimation From Free-viewpoint Surveillance Camera
Toshiaki Hirooka; Hiroki Takahashi
Oral presentation, Japanese, 信学技報, Domestic conference
19 Feb. 2019 - Street Gutter Extraction Focusing on Boundaries Between Road and Street Gutter
Masataka Kudou; Hiroki Takahashi
Oral presentation, Japanese, 信学技報, Domestic conference
19 Feb. 2019 - Detection of Improper Tactile Paving using Pedestrian Viewpoint Video
Kento Watanabe; Hiroki Takahashi
Oral presentation, Japanese, 信学技報, Domestic conference
19 Feb. 2019 - Illumination Estimation Based on Photometric Consistency Perception for AR
Yuki Oyama; Hiroki Takahashi
Oral presentation, Japanese, 信学技報, Domestic conference
19 Feb. 2019 - Binary Action Segmentation Based on SVM and Graphcuts for Sign Language Words Annotation Assistance
Natsuki Takayama; Hiroki Takahashi
Oral presentation, Japanese, NICOGRAPH 2018, Domestic conference
02 Nov. 2018 - 3D Camera Pose Estimation from Concatenated Segments Matching
Zhengnan Yu; Hiroki Takahashi
Oral presentation, English, NICOGRAPH 2018, Domestic conference
02 Nov. 2018 - 手話単語認識を用いたアノテーション支援の検討
Natsuki Takayama; Hiroki Takahashi
Poster presentation, Japanese, 21st Meeting on Image Recognition and Understanding, Domestic conference
05 Aug. 2018 - Multi-postures Human Extraction Using Coarse-to-Fine Method
Yosuke Kinoshita; Hiroki Takahashi
Oral presentation, Japanese, ITE Technical Report, Domestic conference
16 Mar. 2018 - Cloth Model Fitting for Laundry Folding Support
Megumi Kido; Hiroki Takahashi
Oral presentation, Japanese, ITE Technical Report, Domestic conference
16 Mar. 2018 - Non-planar marker detection by adaptive division marker for AR
Tao Iwasaki; Hiroki Takahashi
Oral presentation, Japanese, ITE Technical Report, Domestic conference
16 Mar. 2018 - 3D Camera Pose Estimation from Corresponding Segments
Zhengnan Yu; Hiroki Takahashi
Oral presentation, English, ITE Technical Report, Domestic conference
16 Mar. 2018 - Annotation Assistant using Words Recognition for Building Japanese Sign Language Corpus
Natsuki Takayama; Hiroki Takahashi
Oral presentation, Japanese, ITE Technical Report, Domestic conference
16 Mar. 2018 - 幾何学的線形特徴を用いた車載動画からの側溝領域抽出
Masataka Kudo; Hiroki Takahashi
Oral presentation, Japanese, The Institute of Image Electronics Engineers of Japan, Domestic conference
01 Mar. 2018 - 視覚障害者誘導用ブロック欠損判定のための歩行者視点動画解析
Kento Watanabe; Hiroki Takahashi
Oral presentation, Japanese, The Institute of Image Electronics Engineers of Japan, Domestic conference
01 Mar. 2018 - Skin Analysis Using Active Segmentation Mesh
Yuriko Kobayashi; Hiroki Takahashi
Oral presentation, Japanese, ITE Technical Report, Domestic conference
16 Feb. 2018 - 携帯品に頑健な背面歩容識別
Toshiaki Hirooka; Hiroki Takahashi
Poster presentation, Japanese, The 20th Meeting on Image Recognition and Understanding, Domestic conference
07 Aug. 2017 - Robust Gait Identification with Belongings From Back View
Toshiaki Hirooka; Hiroki Takahashi
Poster presentation, Japanese, ITE Technical Report, Domestic conference
14 Mar. 2017 - Street Gutter Region Extraction Using Projective Geometric Features
Masataka Kudou; Hiroki Takahashi
Oral presentation, Japanese, ITE Technical Report, Domestic conference
14 Mar. 2017 - Deficient Tactile Paving Surfaces Judgement
Kento Watanabe; Hiroki Takahashi
Oral presentation, Japanese, ITE Technical Report, Domestic conference
14 Mar. 2017 - Illumination Estimation Based on Human Visual Characteristics
Yuki Oyama; Hiroki Takahashi
Oral presentation, Japanese, ITE Technical Report, Domestic conference
14 Mar. 2017 - Personal Identification Using Appearance Information for Surveillance System
Fitria Yuningsih; Hiroki Takahashi
Oral presentation, English, The Institute of Image Electronics Engineers of Japan, 長崎, Domestic conference
09 Mar. 2017 - Eye Gesture Identification that Robust to Head Posture Change for Mobile Device
Seiya Niii; Hiroki Takahashi
Oral presentation, Japanese, ITE Technical Report, Domestic conference
20 Feb. 2017 - Operation of Gaze Input Device Based on Target Selection Model
Fumihiro Kobayashi; Hiroki Takahashi
Oral presentation, Japanese, ITE Technical Report, Domestic conference
20 Feb. 2017 - プライバシ保護のための風貌変換
Ryuichiro Goda; Hiroki Takahashi
Oral presentation, Japanese, ITE Technical Report, Domestic conference
20 Feb. 2017 - Skin Analysis Using Sulcus Cutis Extraction
Christopher Tse; Chikako Shibata; Hiroki Takahashi
Oral presentation, English, 第163回情報処理学会コンピュータグラフィックスとビジュアル情報学研究会, Domestic conference
05 Sep. 2016 - CBIR Using Combination of Color and Texture Descriptors
Daniel Caballero Garcia; Hiroki Takahashi; Mariko Nakano Miyatake
Oral presentation, English, 第163回情報処理学会コンピュータグラフィックスとビジュアル情報学研究会, Domestic conference
05 Sep. 2016 - リンゴの表面反射特徴計測を用いた熟度評価
Yuriko Kobayashi; Hiroki Takahashi
Oral presentation, Japanese, ITE Technical Report, Domestic conference
09 Mar. 2016 - キメ分析に基づく肌状態変化計測
Chikako Shibata; Natuki Takayama; Hiroki Takahashi
Oral presentation, Japanese, ITE Technical Report, Domestic conference
09 Mar. 2016 - 速度不変特徴量を用いた動作識別
Tomonori Kuno; Hiroki Takahashi
Oral presentation, Japanese, ITE Technical Report, Domestic conference
09 Mar. 2016 - スライドインタフェースのためのジェスチャ識別を用いたマーキング操作
Reina Hayasaka; Natuki Takayama; Hiroki Takahashi
Poster presentation, Japanese, ITE Technical Report, Domestic conference
09 Mar. 2016 - カメラフォーカシングに基づくブラー差分を用いた被写体抽出
Natuki Takayama; Hiroki Takahashi
Oral presentation, Japanese, Visual Computing Workshop 2015, The journal of the Institute of Image Electronics Engineers of Japan : visual computing, devices & communications, Domestic conference
27 Nov. 2015 - ダンス上達のためのダウン動作リズム解析
Nagatoshi Hayabusa; Hiroki Takahashi
Oral presentation, Japanese, Visual Computing Workshop 2015, The journal of the Institute of Image Electronics Engineers of Japan : visual computing, devices & communications, Domestic conference
27 Nov. 2015 - 個人同定秘匿を維持した段階的な情報開示の可能性
Ryuichiro Goda; Hiroki Takahashi
Poster presentation, Japanese, ITE Technical Report, Domestic conference
14 Mar. 2015 - 車線予測モデルを用いた視界不良時の車線追跡
Jun Shiwaku; Hiroki Takahashi
Oral presentation, Japanese, DIA2015, Domestic conference
05 Mar. 2015 - 視聴者の興奮度に基づいたスポーツ映像の自動ハイライト作成
Tatsuya Sasaki; Hiroki Takahashi
Oral presentation, Japanese, DIA2015, Domestic conference
05 Mar. 2015 - Plane of Uneven Polygonal Surface Extraction for Vision-Based Augmented Reality
Tao Iwasaki; Natsuki Takayama; Nagatoshi Hayabusa; Hiroki Takahashi
Oral presentation, Japanese, The Institute of Image Electronics Engineers of Japan, Domestic conference
27 Feb. 2015 - Target Selection Based on Gaze Likelihood on Eye Interface
Fuhihiro Kobayashi; Hiroki Takahashi
Oral presentation, Japanese, The Institute of Image Electronics Engineers of Japan, Domestic conference
27 Feb. 2015 - Gaze Gesture Classification for Paging Operation in Mobile Device
Seiya Niii; Kazuma Miyanabe; Natsuki Takayama; Hiroki Takahashi
Oral presentation, Japanese, ITE Technical Report, Domestic conference
23 Feb. 2015 - Operator Independent Gesture Identification for Multiuser Slide Interface
Kazuma Miyanabe; Hiroki Takahashi
Oral presentation, Japanese, ITE Technical Report, Domestic conference
23 Feb. 2015 - Accuracy Evaluation of Menu Selection Interface using Saccade
Takahiro Fukaya; Natsuki Takayama; Hiroki Takahashi
Oral presentation, Japanese, Proceedings of the Media Computing Conference, The Institute of Image Electronics Engineers of Japan, Domestic conference
29 Jun. 2014 - Robust Estimation of Hand Posture for Self-occlusion
Naoki Endo; Hiroki Takahashi
Poster presentation, Japanese, ITE Technical Report, Domestic conference
17 Mar. 2014 - Facial Expression Recognition from Incomplete Information
Ryoichi Hirasawa; Hiroki Takahashi
Poster presentation, Japanese, ITE Technical Report, Domestic conference
17 Mar. 2014 - スライド操作ンタフェーにおける安定したポインティグ位置推定のため動的時間平滑化
Kazuma Miyanabe; Hiroki Takahashi
Oral presentation, Japanese, DIA2014, Domestic conference
07 Mar. 2014 - Scene Analysis for Transpiling Representation at Indoor Navigation
Mitsushige Komiya; Hiroki Takahashi
Oral presentation, Japanese, The Institute of Image Electronics Engineers of Japan, Domestic conference
28 Feb. 2014 - Menu Selection Interface using Saccade
Takahiro Fukaya; Hiroki Takahashi
Oral presentation, Japanese, The Institute of Image Electronics Engineers of Japan, Domestic conference
28 Feb. 2014 - Ground Truth Generation based on Spatio-temporal Properties of Lane Markers
Jun Shiwaku; Hiroki Takahashi
Oral presentation, Japanese, IEICE Technical Report, Domestic conference
18 Feb. 2014 - Individual Identification by Using Rear Gait Feature
Genki Momose; Hiroki Takahashi
Oral presentation, Japanese, ITE Technical Report, Domestic conference
18 Feb. 2014 - Gaze Gesture Estimation by Gaze Angle Variation
Naoya Takeuchi; Hiroki Takahashi
Oral presentation, Japanese, IEICE Technical Report, Domestic conference
14 Feb. 2014 - Halftone image representation for Choshi Design System
Natsuki Takayama; Hiroki Takahashi
Oral presentation, Japanese, ITE Technical Report
10 Dec. 2013
Dec. 2013 Dec. 2013 - Hierarchical region representation for Choshi Design System
Natsuki Takayama; Hiroki Takahashi
Oral presentation, Japanese, NICOGRAPH 2013
08 Nov. 2013 - Transpirling Representation for Indoor Navigation
Mitsushige Komiya; Hiroki Takahashi
Poster presentation, Japanese, NICOGRAPH 2013, Domestic conference
08 Nov. 2013 - Rear Gait Feature for Individual Recognition
Genki Momose; Hiroki Takahashi
Poster presentation, Japanese, NICOGRAPH 2013, Domestic conference
08 Nov. 2013 - Paging Operation by Gaze Gesture for Mobile Devices
Naoya Takeuchi; Hiroki Takahashi
Poster presentation, Japanese, NICOGRAPH 2013, Domestic conference
08 Nov. 2013 - Menu Selection Interface using Eye Gaze
Takahiro Fukaya; Hiroki Takahashi
Poster presentation, Japanese, NICOGRAPH 2013, Domestic conference
08 Nov. 2013 - 味覚印象に影響を及ぼす視覚感性効果の解析
Haruka Kobayashi; Hiroki Takahashi
Oral presentation, Japanese, ITE Technical Report
Mar. 2013 - Transpiring Stroll Information Representation
Atsumi Taketomi; Hiroki Takahashi
Oral presentation, Japanese, ITE Technical Report
Mar. 2013 - Ground Truth Generation Using Geometrical Lane Makers Features for Lane Detection
Jun Shiwaku; Hiroki Takahashi
Oral presentation, Japanese, ITE Technical Report
Mar. 2013 - Surface Estimation of AR Marker on Cylindrical Objects
Naoki Kanayama; Hiroki Takahashi
Oral presentation, Japanese, ITE Technical Report
Mar. 2013 - Hand Gesture Interface for Rotation Operation
Yasuaki Ishida; Hiroki Takahashi
Oral presentation, Japanese, ITE Technical Report
Mar. 2013 - Video Face Swapping based on Facial Expression
Koyuki Hayakawa; Hiroki Takahashi
Oral presentation, Japanese, ITE Technical Report
Nov. 2012 - 3D Gait Data Analysis for Person Authentication
Genki Momose; Hiroki Takahashi
Oral presentation, Japanese, ITE Technical Report
Nov. 2012 - Hierarchical Book Cover Image Retrieval with Multiple Features for Book Management
Feiling He; Hiroki Takahashi
Oral presentation, Japanese, The Institute of Image Electronics Engineers of Japan
Mar. 2012 - Jump Analysis for Supporting Physical Exercise on Mentally-retarded Children
Nagatoshi Hayabusa; Hiroki Takahashi
Oral presentation, Japanese, The Society for Art and Science
Mar. 2012 - Gaze Tracking for Mobile Devices Operation
Naoya Takeuchi; Hiroki Takahashi
Oral presentation, Japanese, IEICE Technical Report
Mar. 2012 - Video Face Swapping based on Time-Sequential Coherence in Facial Expression Transformations
Koyuki Hayakawa; Hiroki Takahashi
Oral presentation, Japanese, ITE Technical Report
Mar. 2012 - An Oversight Prevention Method for an Incorrect Direction for Electrolytic Capacitors based on Visual Stimulus
Ryuichiro Takashima; Hiroaki Kozuka; Nagatoshi Hayabusa; Hiroki Takahashi
Oral presentation, Japanese, ITE Technical Report
Mar. 2012 - Gait Feature Value Analysis for Personal Identification Concealment
Genki Momose; Hiroki Takahashi
Oral presentation, Japanese, ITE Technical Report
Mar. 2012 - First-person Vision System for Observing a Relief
Shota Kamimura; Hiroki Takahashi
Oral presentation, Japanese, ITE Technical Report
Mar. 2012 - Real-time Lane Tracking Based on Lane Feature for Low Visibility Driving
Hiroya Iwaki; Hiroki Takahashi
Oral presentation, Japanese, IEICE Technical Report
Feb. 2012 - Various Recipe Recommendation Based on Personal Preference and Effective Use of Surplus Ingredients
Misato Mochizuki; Hiroki Takahashi
Oral presentation, Japanese, ITE Technical Report
Feb. 2012 - Jumping Movement Support Application for Students with Special Needs Education
Atsumu Watanabe; Nagatoshi Hayabusa; Naoya Takeuchi; Hiroki Takahashi
Oral presentation, Japanese, The Society for Art and Science
Nov. 2011 - マーカを用いた一人称視点透視による拡張空間生成
Atsumu Watanabe; Hiroki Takahashi
Oral presentation, Japanese, NICOGRAPH Spring Annual Conference
Mar. 2011 - バーチャル試着システムのための任意視点表示手法
Shiho Nanba; Hiroki Takahashi
Oral presentation, Japanese, NICOGRAPH Spring Annual Conference
Mar. 2011 - レーザポインタを用いたプレゼンテーションの遠隔操作
Kotarou Yamabe; Hiroki Takahashi
Oral presentation, Japanese, NICOGRAPH Spring Annual Conference
Mar. 2011 - 3次元復元のための能動的映像取得手法
Okito Kagechika; Hiroki Takahashi
Oral presentation, Japanese, NICOGRAPH Spring Annual Conference
Mar. 2011 - 視覚特性を考慮した目視検査支援システム
Satoshi Miyosawa; Hiroki Takahashi
Oral presentation, Japanese, NICOGRAPH Spring Annual Conference
Mar. 2011 - Real-time Lane Detection Using a Lane Model for Drivers at Nighttime
Hiroya Iwaki; Hiroki Takahashi
Oral presentation, Japanese, ITE Technical Report
Feb. 2011 - Choshi Generation System by Stylizing Colors and Shapes
Shubing Meng; Hiroki Takahashi
Oral presentation, English, The society of Art and Science
Mar. 2010 - 空間認知補助のための経路案内情報の浸透的可視化
Kayoko Komatsu; Hiroki Takahashi
Oral presentation, Japanese, NICOGRAPH Spring Festival in TAF
Mar. 2010 - 手遊び学習支援システムのための状態遷移に基づく動作判定
Masao Fujinohara; Hiroki Takahashi
Oral presentation, Japanese, NICOGRAPH Spring Festival in TAF
Mar. 2010 - プリミティブを用いたスケッチによる3次元モデル検索
Hiroaki Kozuka; Hiroki Takahashi
Oral presentation, Japanese, NICOGRAPH Spring Festival in TAF
Mar. 2010 - モバイル電子透かしのための部分画像からの透かし検出
Misato Mochizuki; Hiroki Takahashi
Oral presentation, Japanese, NICOGRAPH Spring Festival in TAF
Mar. 2010 - 視界不良時におけるドライバ補助のための浸透的可視化
Hiroya Iwaki; Hiroki Takahashi
Oral presentation, Japanese, NICOGRAPH Spring Festival in TAF
Mar. 2010 - SIGGRAPH 2009 paper summary
Hiroki Takahashi
Oral presentation, Japanese, ITE Technical Paper
Oct. 2009 - 3D model generation method from some hand-drawn character image
Nobuhiro Igata; Hiroki Takahashi
Oral presentation, Japanese, NICOGRAPH Spring Festival in TAF
Mar. 2009 - Transpiring Visualization for Intuitive Navigation
Shinji Igarashi; Hiroki Takahashi
Oral presentation, Japanese, NICOGRAPH Spring Festival in TAF
Mar. 2009 - Transpring Visualizatim for Transportable Information in Disruption to Railway Services
Misaki Soma; Hiroki Takahashi
Oral presentation, Japanese, NICOGRAPH Spring Festival in TAF
Mar. 2009 - Knee arthrodial cartilage extraction from MRI based on Graph Cut
Yuzuru Sano; Hiroki Takahashi
Oral presentation, Japanese, NICOGRAPH Spring Festival in TAF
Mar. 2009 - A Robust Laser Point Extraction Method
Naoki Yatsuda; Hiroki Takahashi
Oral presentation, Japanese, NICOGRAPH Spring Festival in TAF
Mar. 2009 - Saliency-based Extraction for Candidate Inspection Regions in Tape Automated Bonding
Akiko Takakura; Hiroki Takahashi
Oral presentation, Japanese, NICOGRAPH Spring Festival in TAF
Mar. 2009 - Interactive Presentation System Based on Hand Gesture
Takeshi Hiramatsu; Hiroki Takahashi
Oral presentation, Japanese, NICOGRAPH Spring Festival in TAF
Mar. 2009 - SIGGRAPH 2008 paper summary
Hiroki Takahashi
Oral presentation, Japanese, ITE Technical Paper
Oct. 2008 - 2次元画像からの彫紙作製システムの構築
高山夏樹; 高橋裕樹
Oral presentation, Japanese, Proceedings of the 4th Digital Contents Symposium
Jun. 2008 - プレゼンテーション支援のためのレーザポインタによる柔軟な描画手法
箕田大祐; 高橋裕樹
Oral presentation, Japanese, CGアニメーションカンファレンスNICOGRAPH Spring Festival in TAF,NICOGRAPH春季大会
Mar. 2008 - トレーニング支援のための骨盤矢状傾斜計測手法の検討
早房長敏; 高橋裕樹
Oral presentation, Japanese, CGアニメーションカンファレンスNICOGRAPH Spring Festival in TAF,NICOGRAPH春季大会
Mar. 2008 - 2次元画像からの彫紙作製システムの検討
高山夏樹; 高橋裕樹
Oral presentation, Japanese, CGアニメーションカンファレンスNICOGRAPH Spring Festival in TAF,NICOGRAPH春季大会
Mar. 2008 - 画像属性を用いたビデオのグラフ構造
佐野譲; 高橋裕樹
Oral presentation, Japanese, CGアニメーションカンファレンスNICOGRAPH Spring Festival in TAF
Mar. 2007 - マンガ構成要素の特徴解析
井形進宏; 高橋裕樹; 児玉幸子
Oral presentation, Japanese, CGアニメーションカンファレンスNICOGRAPH Spring Festival in TAF
Mar. 2007 - 異なる光源下におけるフォーカルカラー選定の変化に関する研究--デジタルシネマにおける忠実な色再現に関する基礎研究--
岡村光展; 張英夏; 齋藤豪; 川上一郎; 高橋裕樹; 中嶋正之
Oral presentation, Japanese, 第2回デジタルコンテンツシンポジウム,第2回デジタルコンテンツシンポジウム
Jun. 2006 - HMM を用いた毛筆調レンダリングに関する研究第二報-HMM クラスタリングによる実行時間の短縮-
岡部雄太; 齋藤豪; 高橋裕樹; 中嶋正之
Oral presentation, Japanese, 情報処理学会,第68回全国大会
Mar. 2006 - 物体中の各部分に関する日本語表現と3Dモデルとの対応
京田文人; 齋藤豪; 高橋裕樹; 中嶋正之
Oral presentation, Japanese, 電子情報通信学会,2006総合大会
Mar. 2006 - A Novel Approach for Detection of Position of the Tongue in a Frontal View
Luis Sapaico; Hiroki Takahashi; Suguru Saito; Masayuki Nakajima
Oral presentation, English, 電子情報通信学会,2006総合大会
Mar. 2006 - 逐次状態分割法を用いたモデル化による開扉動作の生成
平川裕樹; 齋藤豪; 高橋裕樹; 中嶋正之
Oral presentation, Japanese, 電子情報通信学会,2006総合大会
Mar. 2006 - 斜面歩行の動作に関する研究
石井幹晴; 船津聡; 高橋裕樹; 齋藤豪; 中嶋正之
Oral presentation, Japanese, 電子情報通信学会,2006総合大会
Mar. 2006 - Morphological Scale Space based Color Segmentation
David Gavilan; Hiroki Takahashi; Suguru Saito; Masayuki Nakajima
Oral presentation, English, 電子情報通信学会,2006総合大会
Mar. 2006 - モーションキャプチャにおけるボディキャリブレーション
近藤悟; 高橋裕樹; 齋藤豪; 中嶋正之
Oral presentation, Japanese, 電子情報通信学会,2006総合大会
Mar. 2006 - SIGGRAPH2005論文発表解説
高橋 裕樹
Others, Japanese, 月例セミナー, 芸術科学会
Sep. 2005 - 2 値エッジ画像に基づくオブジェクト輪郭推定法-接ベクトル導出の改善に関する検討-
辻裕之; 徳増眞司; 齋藤豪; 高橋裕樹; 中嶋正之
Oral presentation, Japanese, FIT2005(第4回情報科学技術フォーラム)
Sep. 2005 - 線の延長可能性を表す場を用いた不連続な輪郭線の延長法
岡本穏; 齋藤豪; 高橋裕樹; 中嶋正之
Oral presentation, Japanese, 電子情報通信学会,画像の認識・理解シンポジウム(MIRU2005)
Jul. 2005 - A Multiscale Decomposition of Point-sampled 3D Objects
Hamid LAGA; Hiroki Takahashi; Suguru Saito; Masayuki Nakajima
Oral presentation, English, 情報処理学会,グラフィクスとCAD研究会
May 2005 - 円柱光学系を考慮したフラットベッド型イメージスキャナによる超高精細三次元再構成
周藤一浩; 齋藤豪; 高橋裕樹; 中嶋正之
Oral presentation, Japanese, VC/GCAD合同シンポジウム2005
May 2005 - 多様な物体形状に対する把持姿勢の決
京田文人; 齋藤豪; 高橋裕樹; 中嶋正之
Oral presentation, Japanese, 電子情報通信学会,2005総合大会
Mar. 2005 - モーションキャプチャにおけるボディキャリブレーション
近藤悟; 高橋裕樹; 齋藤豪; 中嶋正之
Oral presentation, Japanese, 電子情報通信学会,2005総合大会
Mar. 2005 - 2値エッジ画像に基づくオブジェクト輪郭推定法の検討
辻裕之; 徳増眞司; 齋藤豪; 高橋裕樹; 中嶋正之
Oral presentation, Japanese, 電子情報通信学会,2005総合大会
Mar. 2005 - Virtual Vision System for Autonomous Agents
Gael Vasseur; Fumihito Koyama; Suguru Saito; Hiroki Takahashi; Masayuki Nakajima
Oral presentation, English, 電子情報通信学会,2005総合大会
Mar. 2005 - 連続HMMを用いた開扉時の移動動作生成
平川裕樹; 齋藤豪; 高橋裕樹; 中嶋正之
Oral presentation, Japanese, 電子情報通信学会,2005総合大会
Mar. 2005 - キャラクタアニメーションのための動作の接続
新井洋平; 船津聡; 高橋裕樹; 齋藤豪; 中嶋正之
Oral presentation, Japanese, 電子情報通信学会,2005総合大会
Mar. 2005 - 立体視におけるフレーム遅延が眼精疲労等に与える影響
油井慶康; 高橋裕樹; 中嶋正之
Oral presentation, Japanese, 電子情報通信学会,2005総合大会
Mar. 2005 - A Scale-space Approach for Features of Intermediate Complexity Detection from Point-sampled 3D Objects
Hamid Laga; Hiroki Takahashi; Suguru Saito; Masayuki Nakajima
Oral presentation, English, 電子情報通信学会,2005総合大会
Mar. 2005 - Analyzing Color Information Oriented to Text Images from Natural Scenes
Yang Xiaoheng; Hiroki Takahashi; Masayuki Nakajima
Oral presentation, English, 電子情報通信学会,2005総合大会
Mar. 2005 - Realistic fish model for real-time interactive system
Srisombut Preechaya; Hiroki Takahashi; Masayuki Nakajima
Oral presentation, English, 電子情報通信学会,2005総合大会
Mar. 2005 - 多様な曲率を持つストローク生成のための毛筆調レンダリングの改良
岡部雄太; 齋藤豪; 高橋裕樹; 中嶋正之
Oral presentation, Japanese, 情報処理学会,第67回全国大会
Mar. 2005 - 縮小光学系を考慮したフラットベット型イメージスキャナによる超高精細三次元再構成
周藤一浩; 齋藤豪; 高橋裕樹; 中嶋正之
Oral presentation, Japanese, 情報処理学会,第67回全国大会
Mar. 2005 - 線の延長可能性を表す場を用いた不連続な輪郭線の延長法
岡本穏; 齋藤豪; 高橋裕樹; 中嶋正之
Oral presentation, Japanese, 情報処理学会,第67回全国大会
Mar. 2005 - Perception-based Evaluation of Segmentation Algorithm
David Gavilan Ruiz; Hiroki Takahashi; Suguru Saito; Masayuki Nakajima
Oral presentation, English, 情報処理学会,第67回全国大会
Mar. 2005 - 水中画像を利用した水泳アニメーションの作成
野地朱真; 高橋裕樹; 中嶋正之
Oral presentation, Japanese, 第20回NICOGRAPH論文コンテスト論文集
Nov. 2004 - 低ビットレート映像符号化への適用を目的とした非等方拡散法の時空間3次元への拡張に関する検討
辻裕之; 徳増眞司; 高橋裕樹; 中嶋正之
Oral presentation, Japanese, 信学技報
Jul. 2004 - 非等方拡散法に基づく空間平滑化フィルタの構築に関する検討
辻裕之; 徳増眞司; 高橋裕樹; 中嶋正之
Oral presentation, Japanese, 信学技報
May 2004 - 光線ボリュームバッファを用いたボリュームとポリゴンの混在シーンの生成方法第4報-グラフィックスハードウエアGPUを用いた高速化-
梶原景範; 高橋裕樹; 中嶋正之
Oral presentation, Japanese, 電子情報通信学会,2004総合大会
Mar. 2004 - A framework for anthopometrical facial rejuvenation
Azam Bastanfard; Hiroki Takahashi; Masayuki Nakajima
Oral presentation, English, 電子情報通信学会,2004総合大会
Mar. 2004 - フレーム遅延が立体視に与える影響-フレーム遅延とオブジェクト色・背景色との関係-
油井慶康; 高橋裕樹; 中嶋正之
Oral presentation, Japanese, 電子情報通信学会,2004総合大会
Mar. 2004 - A new virtual interface for the foot motion sensing CAVE
Barrera Salvador; Hiroki Takahashi; Masayuki Nakajima
Oral presentation, English, 電子情報通信学会,2004総合大会
Mar. 2004 - A Method for Text Detection in Natural Scene Against Shadows
Yang Xiaoheng; Hiroki Takahashi; Masayuki Nakajima
Oral presentation, English, 電子情報通信学会,2004総合大会
Mar. 2004 - 非等方拡散法に基づく平滑化フィルタ制御に関する基礎検討
辻裕之; 徳増眞司; 高橋裕樹; 中嶋正之
Oral presentation, Japanese, 電子情報通信学会,2004総合大会
Mar. 2004 - Geometry Image Matching for Similarity Estimation of 3D Shapes
Hamid Laga; Piperakis Romanos; Hiroki Takahashi; Masayuki Nakajima
Oral presentation, English, 電子情報通信学会,2004総合大会
Mar. 2004 - Automatic classification of Uchida-Kraepelin Test using Feed-Forward Neural Networks
Akbari Mohammad Ali; Momoto Uchida; Hiroki Takahashi; Masayuki Nakajima
Oral presentation, English, 電子情報通信学会,2004総合大会
Mar. 2004 - Image Indexing using Color Blobs
David Gavilan Ruiz; Hiroki Takahashi; Masayuki Nakajima
Oral presentation, English, 電子情報通信学会,2004総合大会
Mar. 2004 - TVMLを用いた生番組自動生成
田中紀成; 林正樹; 高橋裕樹; 中嶋正之
Oral presentation, Japanese, 電子情報通信学会,2004総合大会
Mar. 2004 - イメージスキャナを用いた超高精細3 次元再構成
山口晃弘; 齋藤豪; 高橋裕樹; 中嶋正之
Oral presentation, Japanese, 電子情報通信学会,2004総合大会
Mar. 2004 - TVMLを用いたテレビ番組自動生成のための台本記述法
青木里枝; 林正樹; 高橋裕樹; 中嶋正之
Oral presentation, Japanese, 電子情報通信学会,2004総合大会
Mar. 2004 - 不連続な輪郭線に対する塗りつぶしのための場の推定
中村亜希子; 齋藤豪; 高橋裕樹; 中嶋正之
Oral presentation, Japanese, 電子情報通信学会,2004総合大会
Mar. 2004 - 撮影したフットプリントデータを用いた毛筆調レンダリングに関する研究
岡部雄太; 齋藤豪; 高橋裕樹; 中嶋正之
Oral presentation, Japanese, 電子情報通信学会,2004総合大会
Mar. 2004 - 立体視におけるフレーム遅延の検出と復旧
近藤悟; 高橋裕樹; 中嶋正之
Oral presentation, Japanese, 電子情報通信学会,2004総合大会
Mar. 2004 - 仮想電子図書館のための動作入力システムの検討
平川裕樹; Pramual Suteecharuwat; 高橋裕樹; 中嶋正之
Oral presentation, Japanese, 電子情報通信学会,2004総合大会
Mar. 2004 - モーションキャプチャデータの動作学習
井口雅之; Piperakis Romanos; 齋藤豪; 高橋裕樹; 中嶋正之
Oral presentation, Japanese, 電子情報通信学会,2004総合大会
Mar. 2004 - A Gesture-Based Interface for the Presentation Control
Srisombut Preechaya; Pramual Suteecharuwat; Hiroki Takahashi; Masayuki Nakajima
Oral presentation, English, 電子情報通信学会,2004総合大会
Mar. 2004 - Drape Appearance on Cloths Using Gabor Wavelats
Azam Bastanfard; Hiroki Takahashi; Masayuki Nakajima
Oral presentation, English, 第19回NICOGRAPH論文コンテスト論文集
Nov. 2003 - Ubiquitous Image Categorization using Color Blobs
David Gavilan Ruiz; Hiroki Takahashi; Masayuki Nakajima
Oral presentation, English, 第19回NICOGRAPH論文コンテスト論文集
Nov. 2003 - 非等方拡散法に基づく時空間平滑化処理とその動符号化への応用
辻裕之; 徳増眞司; 高橋裕樹; 中嶋正之
Oral presentation, Japanese, 第19回NICOGRAPH論文コンテスト論文集
Nov. 2003 - 不完全なエッジ情報に基づくオブジェクト領域抽出法の検討
辻裕之; 徳増眞司; 高橋裕樹; 中嶋正之
Oral presentation, Japanese, 第8回映像メディア処理シンポジウム(IMPS2003)
Nov. 2003 - SIGGRAPH2003論文の概要報告
高橋 裕樹
Others, Japanese, 月例セミナー, 芸術科学会
Aug. 2003 - 力学を用いたサーカスゲームのエデュテーメント-力学と創造性の教育支援-
野地朱真; 高橋裕樹; 中嶋正之
Oral presentation, Japanese, 映情学技報
Jul. 2003 - A New Method For Fabric Buckling Visualization Based on Gabor Wavelets
Azam Bastanfard; Hiroki Takahashi; Masayuki Nakajima
Oral presentation, English, 映情学技報
Jul. 2003 - Boundary Constraints based Implicit Representation and Reconstruction of Complex 3D Objects
Hamid Laga; Hiroki Takahashi; Masayuki Nakajima
Oral presentation, English, 映情学技報
Jul. 2003 - Color Blobs based Image Categorization for Mobile Devices
David Gavilan Ruiz; Hiroki Takahashi; Masayuki Nakajima
Oral presentation, Japanese, 映情学技報
Jul. 2003 - 電磁気式3 次元位置センサの簡易誤差補正手法の検討
曽我部聡; 高橋裕樹; 中嶋正之
Oral presentation, Japanese, ヒューマンインタフェース学会研究報告集
Jun. 2003 - 仮想環境におけるユーザの負担軽減を考慮した音楽指揮システム
坂口崇裕; 高橋裕樹; 中嶋正之
Oral presentation, Japanese, ヒューマンインタフェース学会研究報告集
Jun. 2003 - 電磁気式3 次元位置センサの簡易誤差補正
曽我部聡; 高橋裕樹; 中嶋正之
Oral presentation, Japanese, 第2回NICOGRAPH 春季大会
May 2003 - Real Time Virtual Interface For Walking on CAVE
Salvador Barrera; Hiroki Takahashi; Masayuki Nakajima
Oral presentation, English, 電子情報通信学会,2003信学総大
Mar. 2003 - Contents Classification in a Mobile Environment: Image Categorization using Color Blobs
David Gavilan Ruiz; Hiroki Takahashi; Masayuki Nakajima
Oral presentation, English, 電子情報通信学会,2003信学総大
Mar. 2003 - A new approach for visualization of texture appearance using Gabor Wavelet
Azam Bastganfard; Hiroki Takahashi; Masayuki Nakajima
Oral presentation, English, 電子情報通信学会,2003信学総大
Mar. 2003 - A Polygon-free based Approach for 3D Shape Transformation
Hamid Laga; Hiroki Takahashi; Masayuki Nakajima
Oral presentation, English, 電子情報通信学会,2003信学総大
Mar. 2003 - 携帯情報端末を利用した情報活用支援システム
小西陽平; 高橋裕樹; 中嶋正之; 橋本直己
Oral presentation, Japanese, 電子情報通信学会,2003信学総大
Mar. 2003 - 計算機支援による実版木からの版画の再現 第一報
山口晃弘; 羽倉弘之; 齋藤 豪; 高橋裕樹; 中嶋正之
Oral presentation, Japanese, 電子情報通信学会,2003信学総大
Mar. 2003 - 光線ボリュームバッファを用いたボリュームとポリゴンの混在シーンの生成方法：第3報-透視投影への拡張-
梶原景範; 高橋裕樹; 中嶋正之
Oral presentation, Japanese, 電子情報通信学会,2003信学総大
Mar. 2003 - 磁気式三次元位置センサの誤差補正に関する研究
曽我部 聡; 橋本直己; 高橋裕樹; 中嶋正之
Oral presentation, Japanese, 電子情報通信学会,2003信学総大
Mar. 2003 - セルアニメーション制作補助のためのビデオセグメンテーション
べ ユンジョン; 高橋裕樹; 中嶋正之
Oral presentation, Japanese, 電子情報通信学会,2003信学総大
Mar. 2003 - 仮想環境における演奏制御システムの構築
坂口崇裕; 橋本直己; 高橋裕樹; 中嶋正之
Oral presentation, Japanese, 電子情報通信学会,2003信学総大
Mar. 2003 - 光線ボリュームバッファを用いたボリュームとポリゴンの混在シーンのレンダリング方法-ボリュームとボリュームの干渉シーンのレンダリングへの拡張-
梶原景範; 高橋裕樹; 中嶋正之
Oral presentation, Japanese, 第18回NICOGRAPH論文コンテスト論文集
Oct. 2002 - 3D Object Reconstruction from Scanned Data using Radial Basis Functions and Volumetric Processing
Hamid Laga; Piperakis Romanos; Hiroki Takahashi; Masayuki Nakajima
Oral presentation, English, 第18回NICOGRAPH論文コンテスト論文集
Oct. 2002 - SIGGRAPH2002論文の概要報告
高橋 裕樹
Others, Japanese, 月例セミナー, 芸術科学会
Aug. 2002 - セルアニメーション制作補助のためのキャラクタ動作データベース構築-第2報: ショット変化検出パラメータの自動決定-
ベユンジョン; 高橋裕樹; 中嶋正之
Oral presentation, Japanese, 情処技報
Aug. 2002 - 情景画像からのハングル文字列領域抽出と字素識別
金大祐; 高橋裕樹; 中嶋正之
Oral presentation, Japanese, 信学技報
May 2002 - 低品質文字認識のための情景文字画像の高品質化手法
高橋裕樹; 尾形幸祐; 中嶋正之
Oral presentation, Japanese, 信学技報
May 2002 - 移動物体への映像投影システムの構築
小出裕子; 橋本直己; 高橋裕樹; 中嶋正之
Oral presentation, Japanese, 映情学技報
Mar. 2002 - 力学によるアクロバット運動のシミュレーション-インタラクティ ブコンテンツ「空中サーカス」開発-
野地朱真; 藤井俊道; 中嶋正之; 高橋裕樹
Oral presentation, Japanese, 映情学技報
Mar. 2002 - 没入型仮想空間における電磁気式トラッキングシステムの誤差の補正
曽我部聡; 橋本直己; 高橋裕樹; 中嶋正之
Oral presentation, Japanese, 電子情報通信学会,2002総合大会
Mar. 2002 - 3次元モデル管理システムの構築
小西陽平; 橋本直己; 高橋裕樹; 中嶋正之
Oral presentation, Japanese, 電子情報通信学会,2002総合大会
Mar. 2002 - PCクラスタのネットワーク帯域によるレンダリング性能の比較
薄井武順; 橋本直己; 高橋裕樹; 中嶋正之
Oral presentation, Japanese, 電子情報通信学会,2002総合大会
Mar. 2002 - 並列化に適した衝突検出アルゴリズム
新保達也; 橋本直己; 高橋裕樹; 中嶋正之
Oral presentation, Japanese, 電子情報通信学会,2002総合大会
Mar. 2002 - 仮想空間における光跡の立体視表現
中村亜希子; 橋本直己; 高橋裕樹; 中嶋正之
Oral presentation, Japanese, 電子情報通信学会,2002総合大会
Mar. 2002 - プロジェクタを用いた3 次元移動物体のためのARシステム
小出裕子; 橋本直己; 高橋裕樹; 中嶋正之
Oral presentation, Japanese, 電子情報通信学会,2002総合大会
Mar. 2002 - シャボン玉のアート表現に関する研究-実写画像からのシャボン玉形状の輪郭抽出-
石井勢津子; 高橋裕樹; 中嶋正之
Oral presentation, Japanese, 電子情報通信学会,2002総合大会
Mar. 2002 - 複数の特徴を用いたシーン内のハングル文字列領域抽出
金大祐; 高橋裕樹; 中嶋正之
Oral presentation, Japanese, 電子情報通信学会,2002総合大会
Mar. 2002 - 光線ボリュームバッファを用いたボリュームとポリゴンの混在シーンの生成方法第2報-ボリュームとボリュームの干渉シーン生成への拡張-
梶原景範; 高橋裕樹; 中嶋正之
Oral presentation, Japanese, 電子情報通信学会,2002総合大会
Mar. 2002 - モーションキャプチャによるジャグリング動作の解析
佐藤貴洋; 橋本直己; 高橋裕樹; 中嶋正之
Oral presentation, Japanese, 電子情報通信学会,2002総合大会
Mar. 2002 - Detecting and Tracking Active Joint Focus in Motion Capture Data
Piperakis Romanos; Suguru Saito; Hiroki Takahashi; Masayuki Nakajima
Oral presentation, English, 電子情報通信学会,2002総合大会
Mar. 2002 - セルアニメーション制作補助のためのキャラクタ動作データベース構築第1報-Shot 変化の自動検出-
ベユンジョン; 高橋裕樹; 中嶋正之
Oral presentation, Japanese, 電子情報通信学会,2002総合大会
Mar. 2002 - ビデオベースによる水泳の忠実なアニメーション作成に関する研究-クロール運動解析とアニメーション-
野地朱真; 高橋裕樹; 中嶋正之
Oral presentation, Japanese, 電子情報通信学会,2002総合大会
Mar. 2002 - Facial Age Declination Animation
Azam Bastanfard; Hiroki Takahashi; Masayuki Nakajima
Oral presentation, English, 電子情報通信学会,2002総合大会
Mar. 2002 - CAVE を用いた大規模演奏制御システムの構築-冗長なジェスチャ からの有意動作の抽出-
坂口崇裕; 橋本直己; 高橋裕樹; 中嶋正之
Oral presentation, Japanese, 電子情報通信学会,2002総合大会
Mar. 2002 - A New Approach for Automatic Reconstruction of 3D Urban Objects
Hamid Laga; Piperakis Romanos; Hiroki Takahashi; Masayuki Nakajima
Oral presentation, English, 電子情報通信学会,2002総合大会
Mar. 2002 - Autonomous agent motion planning for virtual world environments using viewpoint specific depth sensor
Piperakis Romanos; Hiroki Takahashi; Masayuki Nakajima
Oral presentation, English, 映情学技報
Dec. 2001 - ビデオメモシステム構築のための画像からのハングル文字列領域抽出
金大祐; 高橋裕樹; 中嶋正之
Oral presentation, Japanese, 映情学技報
Dec. 2001 - PCクラスタによる3次元物体の衝突検出の並列化
新保達也; 橋本直己; 高橋裕樹; 中嶋正之
Oral presentation, Japanese, 映情学技報
Dec. 2001 - 光線ボリュームバッファを用いたボリューム・ポリゴン混合シーンの発生方法
梶原景範; 高橋裕樹; 中嶋正之
Oral presentation, Japanese, 映情学技報
Dec. 2001 - Obstacle Avoidance for Intelligent Virtual World Agents Using Z-bu®er Sensor
Piperakis Romanos; Hiroki Takahashi; Masayuki Nakajima
Oral presentation, English, 映像情報メディア学会,2001 映情冬季大
Dec. 2001 - Linux-PC clusterとBMRTを用いた安価なオープンソース型CGプロダクションシステム
アグスバニアブディラー; 橋本直己; 高橋裕樹; 中嶋正之
Oral presentation, Japanese, 第17回NICOGRAPH論文コンテスト論文集
Nov. 2001 - Texture/Non-texture Image Synthesis Optimization Dual Approach
Hussein Karam Hussein; Hiroki Takahashi; Masayuki Nakajima
Oral presentation, English, 第17回NICOGRAPH論文コンテスト論文集
Nov. 2001 - 領域特徴を用いたカラー画像セグメンテーション
高橋裕樹; 中嶋正之
Oral presentation, Japanese, 映情学技報
Oct. 2001 - Visualization of Realistic Human Facial Aging and Humam Skin Senility
Azam Bastanfard; Hussein Karam Hussein; Hiroki Takahashi; Masayuki Nakajima
Oral presentation, English, 映情学技報
Oct. 2001 - PC クラスタによる衝突判定を用いた仮想空間の構築
新保達也; 高橋裕樹; 中嶋正之
Oral presentation, Japanese, 電子情報通信学会,2001ソサイエティ大会
Sep. 2001 - 光線ボリュームバッファを用いたボリューム・ポリゴン混合シーンの発生方法
梶原景範; 高橋裕樹; 中嶋正之
Oral presentation, Japanese, 電子情報通信学会,2001ソサイエティ大会
Sep. 2001 - 複数の特徴を用いたシーン内の文字領域抽出
金大祐; 高橋裕樹; 中嶋正之
Oral presentation, Japanese, 電子情報通信学会,2001ソサイエティ大会
Sep. 2001 - 領域エネルギーを用いたカラー画像セグメンテーション
高橋裕樹; 中嶋正之
Oral presentation, Japanese, 電子情報通信学会,2001ソサイエティ大会
Sep. 2001 - 「SIGGRAPH2001報告会」論文の概要報告
高橋 裕樹; 橋本 直己
Others, Japanese, 月例セミナー, 芸術科学会
Aug. 2001 - PCクラスタによるCGプロダクションシステム
アグスバニアブディラー; 橋本直己; 高橋裕樹; 中嶋正之
Oral presentation, Japanese, 信学技報
Jul. 2001 - Foot motion sensing device for the virtual world
Barrera Salvador; Piperakis Romanos; Suguru Saito; Hiroki Takahashi; Masayuki Nakajima
Oral presentation, English, 信学技報
Jul. 2001 - Virtual world modeling for smart agent using neural network
Piperakis Romanos; Suguru Saito; Hiroki Takahashi; Masayuki Nakajima
Oral presentation, English, 信学技報
Apr. 2001 - 没入型仮想空間における奥行き知覚に関する研究
小西陽平; 高橋裕樹; 橋本直己; 中嶋正之
Oral presentation, Japanese, 信学技報
Apr. 2001 - 仮想環境における実時間音響モデル
鶴大輔; 高橋裕樹; 中嶋正之
Oral presentation, Japanese, 映情学技報
Mar. 2001 - View-Dependent Line Rendering手法に関する検討第2報
張英夏; 齋藤豪; 高橋裕樹; 中嶋正之
Oral presentation, Japanese, 情報処理学会,第62回情処全大
Mar. 2001 - Facial age caricaturing
Azam Bastanfard; Hiroki Takahashi; Masayuki Nakajima
Oral presentation, English, 情報処理学会,第62回情処全大
Mar. 2001 - 情景画像からのハングル領域抽出
金大祐; 高橋裕樹; 中嶋正之
Oral presentation, Japanese, 情報処理学会,第62回情処全大
Mar. 2001 - A hybrid connectionist-symbolic approach to intelligent agent design and environmental coupling
Piperakis Romanos; Hiroki Takahashi; Suguru Saito; Masayuki Nakajima
Oral presentation, English, 情報処理学会,第62回情処全大
Mar. 2001 - 実写画像を用いた魚の実時間アニメーション生成システムの構築
山脇敦; 中嶋正之; 高橋裕樹; 橋本直己
Oral presentation, Japanese, 情報処理学会,第62回情処全大
Mar. 2001 - 文字認識のための文字列画像の高品質化に関する研究
尾形幸祐; 高橋裕樹; 中嶋正之
Oral presentation, Japanese, 情報処理学会,第62回情処全大
Mar. 2001 - 複雑な仮想環境における実時間立体音響の生成 第二報
鶴大輔; 高橋裕樹; 中嶋正之
Oral presentation, Japanese, 情報処理学会,第62回情処全大
Mar. 2001 - 没入型仮想空間における奥行き知覚特性に関する研究
小西陽平; 中嶋正之; 高橋裕樹; 橋本直己
Oral presentation, Japanese, 情報処理学会,第62回情処全大
Mar. 2001 - しゃぼん玉のCG 表現に関する研究
ベユンジョン; 齋藤豪; 高橋裕樹; 中嶋正之
Oral presentation, Japanese, 情報処理学会,第62回情処全大
Mar. 2001 - 仮想空間におけるエージェントの知識の獲得
八嶋栄美子; 齋藤豪; 高橋裕樹; 中嶋正之
Oral presentation, Japanese, 情報処理学会,第62回情処全大
Mar. 2001 - 仮想空間におけるエージェントの動作
井元崇之; 齋藤豪; 高橋裕樹; 中嶋正之
Oral presentation, Japanese, 情報処理学会,第62回情処全大
Mar. 2001 - CGプロダクションのための並列分散レンダリングシステム
アグスバニアブディラー; 橋本直己; 高橋裕樹; 中嶋正之
Oral presentation, Japanese, 電子情報通信学会,2001信学総大
Mar. 2001 - A Markov Random Field Based Method for Synthetic Aperture Radar Image Segmentation
Hamid Laga; Hiroki Takahashi; Masayuki Nakajima
Oral presentation, English, 電子情報通信学会,2001信学総大
Mar. 2001 - 領域分割を用いた実写画像からの3 次元モデリング
寺島知宏; 高橋裕樹; 中嶋正之
Oral presentation, Japanese, 電子情報通信学会,2001信学総大
Mar. 2001
Affiliated academic society
Research Themes
- 手話言語等の多文化共生社会に向けたICTを活用したコミュニケーション基盤構築
内海彰; 加藤伸子; 白石優旗
公益財団法人 立石科学技術振興財団, 研究助成, 電気通信大学，筑波技術大学, 研究助成(S), Principal investigator
Apr. 2023 - Mar. 2026 - 東京デフリンピックに向けたAI手話翻訳ツールの活用とボーダーレススポーツイベントの開催
塩田有規; 小松孝行
東京都, 東京都と大学との共同事業, 順天堂大学，電気通信大学, Coinvestigator
Apr. 2023 - Mar. 2024 - 手話言語等の多文化共生社会連携事業講座
高橋裕樹; 内海彰,酒向慎司,齊藤剛史,加藤伸子
経済産業省, 高等教育機関における共同講座創造支援事業, ソフトバンク株式会社，電気通信大学，名古屋工業大学，九州工業大学，筑波技術大学, Others
Oct. 2022 - Feb. 2023 - 聴覚障がい者と健聴者の共生を実現する双方向コミュニケーションシステムに関する研究開発
内海彰; 中鹿亘
ソフトバンク株式会社, 電気通信大学, Principal investigator
Oct. 2017 - Sep. 2022 - 光受容タンパク質を用いた単純細胞受容野型フィルター素子の作製と画像処理
岡田 佳子; 長谷川 裕之; 西岡 一; 高橋 裕樹; 笠井 克幸
日本学術振興会, 科学研究費助成事業, 電気通信大学, 基盤研究(B), 本研究は，光受容タンパク質の視覚機能をデバイスレベルで取り入れた視覚受容野型の画像フィルターを作製し，アナログ画像処理に適用すること，および視覚プロセスを構成論的に明らかにすることを目的とする．本年度は，タンパク質懸濁液をバイオナノインクとしてインクジェット印刷し，網膜神経節細胞受容野および脳の第一視覚野に存在する単純細胞受容野形状を3次元的に模倣した「グレースケール(多値化)DOG / Gaborフィルター」を実現し，アナログ画像処理および錯視検出に適用した．特にGaborフィルターを用いて，代表的な方向錯視であるCafe Wall 錯視を実験的に検出し，心理学実験および計算機シミュレーションと比較した．Cafe wall画像上をフィルター走査するだけで得られる畳み込み画像には，物理的には平行であるモルタル線部に右下がり，右上がりを示すtwisted codeが出現した．さらに錯視の強さに関するGaborフィルターの空間周波数および方位依存性を検討したところ，標準画像の場合には，フィルター長：タイル長が 0.66 以下の場合，および方位0度の場合に錯視が強調されることがわかった．Cafe Wall 錯視は方向依存性のある現象のため，視覚系の方向エンコード機構に基づいて説明することは妥当であり，本結果は錯視の強さが向きや線の長さを検出する神経細胞を模倣したGaborフィルターのサイズ（空間周波数）に依存することを示唆している．人間の目のエッジ検出機能と方向検知機能をソフトウェアや複雑な回路，電源を使わずに生体膜の特性だけで再現することに成功した．, 18H03258
01 Apr. 2018 - 31 Mar. 2022 - Protein-based visual receptive fields for image processing
OKADA-SHUDO YOSHIKO; KASAI Katsuyuki; WARANABE Masayoshi; TANAKA Kazuo; TAKAHASHI Hiroki; TANABE Tokimasa; MUKAI Takayuki; OSAWA Shuhei; FUKAZAWA Hikaru
Japan Society for the Promotion of Science, Grants-in-Aid for Scientific Research, The University of Electro-Communications, Grant-in-Aid for Scientific Research (C), The limited range in which the visual system neurons respond is called a receptive field and is composed of an excitation area and a suppression area showing a potential response of different polarity to the light stimulus. In this study, a photosynthetic protein, bacteriorhodopsin was used as it was, spatial filters that mimic only the structure of receptive fields were prepared and applied to analog image processing. The positive and negative polarity reversal differential responses exhibited by the electrochemical cell are replaced with excitation and repression response of the receptive field, and the element is realized by a very simple method of selectively patterning on the opposite transparent electrode and covering with the mask pattern. Using these image processing elements, real-time image feature detection and comparison with an animal 's electrophysiological response were demonstrated., 15K00226
01 Apr. 2015 - 31 Mar. 2018 - 次世代型携帯メモシステムに関する研究
高橋 裕樹
日本学術振興会, 科学研究費助成事業, 東京工業大学, 奨励研究(A), 本研究では,ビデオカメラで撮影した任意の画像から文字領域を抽出し,認識を行うシステムの作成を目的としている.本年度は特に,抽出対象文字列としてハングルを対象にした研究を中心的に行なった.自然画像からハングルの文字構成の特徴を利用し文字領域を抽出する手法,および,抽出した文字列からハングルを構成する字素を認識する手法について検討を行なった.また,同時に,文字に限定しない領域抽出手法の検討も行なった. 情景画像からのハングル文字領域抽出手法に関する検討では,ハングルの構造特徴を積極的に利用しハングル文字列を抽出する.まず,情景画像から求めた輪郭線から,字素候補を抽出する.その抽出された字素候補に対して,NN(Nearest neighbor)法を改良した手法を適用して,字素候補の絞り込みを行なう.最終的には,ハングルの構成規則を満たす字素候補からハングル文字列を抽出する.実験の結果,491文字のハングルを含む100枚の画像から,約86%にあたる425文字のハングルを抽出できた.さらに,抽出したハングルに対し,細線化を行ない,端点および交点数による字素認識を行なった.細線化においては,Hilditchの細線化手法を改良し,ひげの発生を低減した.100枚の画像に存在するハングルにおいて,字素どうしの接触がない453字素中約72%にあたる326字素が認識できた. また,対象を文字のみに限定せず,任意の対象に対して,物体を一まとまりとして抽出することを目的とした領域分割手法についても検討を行った.画像中の領域の特徴量として,領域境界の輪郭強度,領域の色の統計的な分布などを用いて,隣接領域の統合を行なう領域分割手法について検討を行なった.従来の手法に比べ,視覚的に,物体をあるまとまった領域として抽出することができた., 12780193
2000 - 2001 - 人工生物の協調行動の獲得に関する研究
高橋 裕樹
日本学術振興会, 科学研究費助成事業, 東京工業大学, 奨励研究(A), 本年度の研究においては,人工生物の行動表現に関する研究を中心的に,人工生物の簡易な三次元モデル作成に関する研究も行った. 人工生物の行動表現に関する研究では,仮想金魚の動き,特に群行動の創発に関する研究や水槽中の金魚を複数のカメラで撮影しその動きを抽出し仮想金魚の動きに適用する研究を行った.群行動の創発に関しては,基本的な個体の運動の定義と群の定義をすることにより,魚の群行動を創発することが可能となった.具体的には,補食者と被補食者の定義と自分のまわりの魚の行動にによって自分の行動が影響されるという特性を定義することで,群の集団的な動きを表現することができた.また,画像処理を用いた動きの抽出においては,5(frame/sec)で撮影した映像から、重心位置を抽出し,重心位置の補間および金魚の方向の推定を行い30(frame/sec)での仮想金魚の動きを表現することができた. 人工生物の簡易な三次元モデル作成に関する研究においては,図鑑から入力した魚の画像を用いて,半自動的に魚の三次元モデルを作成する手法について検討を行った.まず始めに,入力された画像から魚部分を抽出し,魚本体とヒレ部分への分割を行った.これは,魚の多くは,身体の部分が楕円体,また,ヒレの部分は平板に近い形状をしていることから,各部位の分割を行った.次に,入力した一枚の画像からは,魚の奥行きデータを推定することが困難であることから,用意した数種類の断面を選択することで,魚の三次元形状を作成した.最終的には,入力画像をテクスチャとして利用し,リアルな魚の三次元モデルを作成した.また,球や円柱などのプリミティブで表現された仮想生物の三次元モデルを自動的に生成する手法についても提案した.提案手法は,芸術的な観点から美しいとされるプロポーションの三次元モデルを作成するものであり,遺伝的アルゴリズムを用いて,均整のとれた体型になる評価関数を定義することで,多様な均整のとれた三次元モデルを作成することができた., 08780250
1996 - 1996
Industrial Property Rights
- 不動産居室画像の構図呈示方法
Patent right, 高橋 裕樹, 赤間 大樹, 木村久男, 鈴木裕介, 鈴木将親, 浅田良夫, 2020-186936, Date applied: 10 Nov. 2020 - 物件情報検索システム、物件情報検索方法、および、物件情報検索プログラム
Patent right, 高橋 裕樹, 小林 菜穂子, 木村 久男, 鈴木 裕介, 鈴木 将親, 浅田 良夫, 2020-000337, 2021-110975 - システム，サーバ装置及びプログラム
Patent right, 高山 夏樹, 高橋 裕樹, 2019-018694, 2020-126144, 6840365 - 光フィルタ素子，これを用いた欠陥検知システム，及び光センサ
Patent right, 岡田佳子, 高橋 裕樹, 向井貴之, 本井拓馬, 田邊李正, 2015-165823, 2017-044526 - 万引き予防システム及びソフトウエア
Patent right, 宮田清蔵, 株式会社日本アレフ, 高橋 裕樹, 高玉圭樹, 2014-184388, 2016-57908 - 磁気式位置計測システムの誤差校正方法
Patent right, 中嶋 正之, 橋本 直己, 高橋 裕樹, 2002-261228, 2004-101273