TABLE OF CONTENTS

Wednesday, May 20, 2009

Session 1: Interaction & Virtual Reality

1-1 Indoor Map Display Method Using Mixed Reality 1
Satoshi Hisanaga and Takaaki Kase, Japan
1-2 Texture Overlay onto Flexible Object with PCA of Silhouettes and K-Means Method for Search into Database 5
Hiroshi Tanaka and Hideo Saito, Japan
1-3 Real-time Motion-based Gesture Recognition Using the GPU 9
Mark Bayazit, Alex Couture-Beil and Greg Mori, Canada

Session 2: Motion & Multiview

2-1 Automatic Gigapixel Mosaicing in Large Scale Unstructured Underground Environments 13
Daniela Craciun, Nicolas Paparoditis and Francis Schmitt, France
2-2 Image Rectification for Robust Matching of Car-mounted Camera Images 17
Naoko Enami, Norimichi Ukita and Masatsugu Kidode, Japan
2-3 Self Image Rectification for Uncalibrated Stereo Video with Varying Camera Motions and Zooming Effects 21
Chia-Ming Cheng, Shang-Hong Lai and Shyh-Haur Su, Taiwan
2-4 A New Method for Projector Calibration Based on Visual Servoing 25
Jérémie Mosnier, Francois Berry and Omar Ait-Aider, France

Session 3: Poster Session 1

3-1 New System Implementation on SIMD Processor for Reliable Fingerprint Singularity Detection by Singular Candidate Method 30
Daisuke Tomizawa, Yuta Hasegawa, Tomohiko Ohtsuka and Hiroyuki Aoki, Japan
3-2 Detection of Abnormal Objects in a Scene Based on Local Features 34
Junya Kobayashi and Keiichi Yamada, Japan
3-3 Real-Time Uncharacteristic-Part Tracking Based on Points Tracking 38
Norimichi Ukita, Akira Makino and Masatsugu Kidode, Japan
3-4 Automatic Extraction of Layer Structure for Retina in OCT Image Using Morphological Operation and Active Net 42
Ai Yamakawa, Shinji Tsuruoka, Hiroharu Kawanaka, Fumio Okuyama and Toshiki Yagi, Japan
3-5 Human Behavior Analysis Using Multiple 2D Features and Multicategory Support Vector Machine 46
Hao-Cheng Mo, Jin-Jang Leou and Cheng-Shian Lin, Taiwan
3-6 Exploitation of 3D Information for Directing Visual Attention and Object Recognition 50
Oytun Akman and Pieter Jonker, Netherlands
3-7 Inter Mode Decision Algorithm For Advanced Video Coding 54
Fang-Hsuan Cheng and Yea-Shuan Huang, Taiwan
3-8 Large-Scale Stereo for Improvement of 3D Measurement Accuracy in Gaze-Observation 58
Masafumi Nakagawa, Yoshihiro Kawai and Fumiaki Tomita, Japan
3-9 An Active Appearance Model with a Derivative-Free Optimization 62
Jixia Zhang, Franck Davoine and Chunhong Pan, China
3-10 Image Forgery Detection Based on Quantization Table Estimation 66
Guo-Shiang Lin, Min-Kuan Chang and You-lin Chen, Taiwan
3-11 A Binarization Method for Crack Detection in a Road Surface Image with the Fractal Dimension 70
Hiromi Yoshida and Naoki Tanaka, Japan
3-12 Building a Multi-Touch Display Based on Computer Vision Techniques 74
Damien Michel, Antonis Argyros, Dimitris Grammenos, Xenophon Zabulis and Thomas Sarmis, Greece
3-13 Synchronization of Full-View Image and GPS Data for Route Map Building 78
Ying Hai, Shigang Li and Yuto Mizuno, Japan
3-14 Study of Early Screening Method of Dementia and Its Systemization 82
Youhei Kondou, Mikiko Kawasumi, Osami Yamamoto, Muneo Yamada, Shin Yamamoto and Tomoaki Nakanno, Japan
3-15 Face Blurring for Privacy in Street-level Geoviewers Combining Face, Body and Skin Detectors 86
Alexandre Devaux, Nicolas Paparoditis, Frédéric Precioso and Bertrand Cannelle, France
3-16 Vision-Based Real-Time Monitoring on the Behavior of Fish School 90
Boon Fong Chew, How-Lung Eng and Myo Thida, Singapore
3-17 Design and Evaluation of Features That Best Define Text in Complex Scene Images 94
Navid Mavaddat, Tae-Kyun Kim and Roberto Cipolla, Australia
3-18 OCR Based Thresholding 98
Yves Rangoni, Faisal Shafait and Thomas M. Breuel, Germany
3-19 A 3.2 kHz, Stereo Sensing Module Using Two Profile Sensors 102
Yoshinori Matsui, Munenori Takumi, Haruyoshi Toyoda, Naohisa Mukozaka, Atsushi Ihori, Yukinobu Sugiyama and Seiichiro Mizuno, Japan
3-20 Video-Based Face Recognition Using a Probabilistic Graphical Model 106
Yi-Chia Chan, Cheng-Chieh Chiang, Kai-Ming Wang and Greg C. Lee, Taiwan
3-21 A Comparative Study of Hierarchical Matching Algorithms for Face Recognition 110
Hajar Momeni, Mohammad T. Sadeghi and Hamid R. Abutalebi, Iran
3-22 1,000-fps Visual Feedback Control of an Active Vision System over a High-Load Network 114
Daisuke Wako, Shingo Kagami and Koichi Hashimoto, Japan
3-23 Image Based View Localization System Retrieving from a Panorama Database by SURF 118
Naoyuki Yazawa, Hideaki Uchiyama, Hideo Saito, Myriam Servières and Guillaume Moreau, Japan
3-24 Hand Shape Recognition Based on Kernel Orthogonal Mutual Subspace Method 122
Yasuhiro Ohkawa and Kazuhiro Fukui, Japan
3-25 Application of Co-Occurrence Frequency Image 126
Takayuki Fujiwara, Hiroyasu Koshimizu and Manabu Hashimoto, Japan
3-26 Improved Matching Accuracy in Traffic Sign Recognition by Using Different Feature Subspaces 130
Arihito Ihara, Hironobu Fujiyoshi, Masanari Takagi, Hiroaki Kumon and Yukimasa Tamatsu, Japan
3-27 Object Pose Estimation Using Patch-Duplet/SIFT Hybrids 134
Fredrik Viksten, Sweden

Session 4: Invited Talk 1

4-1 Large Scale Image Search 138
Dr. Cordelia Schmid, INRIA, France

Session 5: Visual Surveillance

5-1 Probabilistic BPRRC: Robust Change Detection against Illumination Changes and Background Movements 148
Kentaro Yokoi, Japan
5-2 People Re-Identification by Means of a Camera Network Using a Graph-Based Approach 152
Dung-Nghi Truong Cong, Louahdi Khoudour, Catherine Achard and Philippe Phothisane, France
5-3 Incident Detection Based on Dynamic Background Modeling and Statistical Learning Using Spatio-Temporal Features 156
Yasuhiro Murai, Hironobu Fujiyoshi and Masato Kazui, Japan
5-4 Human Head Tracking Based on Inheritance and Evolution Concept 162
Yi Hu and Tetsuya Takamori, Japan
5-5 Unsupervised Abnormal Behavior Detection for Real-Time Surveillance Using Observed History 166
Tsz-Ho Yu and Yiu-Sang Moon, Hong Kong
5-6 Abnormal Spatial Event Detection and Video Content Searching in a Multi-Camera Surveillance System 170
Chueh-Wei Chang, Ti-Hua Yang and Yu-Yu Tsao, Taiwan

Thursday, May 21, 2009

Session 6: Feature Extraction & Pattern Recognition

6-1 Statistical Reach Feature Method and Its Application to Template Matching 174
Ryushi Ozaki, Yutaka Satoh, Kenji Iwata and Katsuhiko Sakaue, Japan
6-2 Design of Feature Extraction Operators for Use on Biologically Motivated Hexagonal Image Structures 178
Sonya Coleman, Bryan Scotney and Bryan Gardiner, United Kingdom
6-3 An Appearance Based Fast Linear Pose Estimation 182
Toshiyuki Amano and Toru Tamaki, Japan
6-4 Semi-Supervised Spectral Mapping for Enhancing Separation between Classes 187
Weiwei Du and Kiichi Urahama, Japan

Session 7: Object Recognition

7-1 Keypoint Extraction and Selection for Object Recognition 191
Maja Rudinac, Boris Lenseigne and Pieter Jonker, Netherlands
7-2 Scene Classification Using Generalized Local Correlation 195
Hideki Nakayama, Tatsuya Harada and Yasuo Kuniyoshi, Japan
7-3 Unsupervised Learning of Characteristic Object Parts from Videos 199
Henrik Skibbe, Alexandra Teynor and Hans Burkhardt, Germany
7-4 Color Image Classification Using Locally Linear Manifolds and Learning 203
Kazuki Kondo and Seiji Hotta, Japan

Session 8: Poster Session 2

8-1 Video Watermarking Algorithm Based on Pseudo 3D DCT and Quantization Index Modulation 207
Hui-Yu Huang, Cheng-Han Yang and Wen-Hsing Hsu, Taiwan
8-2 Overlap Vehicle Detection by Tracking Horizontal Lines 211
Kazunori Onoguchi, Japan
8-3 Measuring Conicity from Shape Boundaries 215
Milos Stojmenovic and Amiya Nayak, Canada
8-4 Image Based Search System Using Hierarchical Object Category Recognition Technique 219
Takuya Minagawa and Hideo Saito, Japan
8-5 Improvement of Particle Filtering for Intersection of Targets with Similar Patterns 223
Naoki Enda, Shinji Fukui, Yuji Iwahori and Robert J. Woodham, Japan
8-6 Voting Based Video Classification Using Clustering and Learning 227
Kei Kikuchi and Seiji Hotta, Japan
8-7 Algorithmic Considerations for Real-Time Stereo Vision Applications 231
Kristian Ambrosch, Christian Zinner and Wilfried Kubinger, Austria
8-8 Behavior Recognition with HMM and Feature Analysis using a Wide-view Camera and a PTZ camera 235
Norimichi Ukita, Akihito Kotera and Masatsugu Kidode, Japan
8-9 A Hardware Accelerator with Variable Pixel Representation & Skip Mode Prediction for Feature Point Detection Part of SIFT Algorithm 239
Jingbang Qiu, Tianci Huang, Yiqing Huang and Takeshi Ikenaga, Japan
8-10 Segmentation of Femoral Head from CT after Femoral Neck Fracture 243
Jan Horáček, Lukáš Maršálek, Martin Horák, Philipp Slusallek and Josef Pelikán, Czech Republic
8-11 Medial Features for Superpixel Segmentation 248
David Engel, Luciano Spinello, Rudolph Triebel, Roland Siegwart, Heinrich H. Bülthoff and Cristóbal Curio, Germany
8-12 Face Recognition by Combining Complementary Matchings of Single Image and Sequential Images 253
Yea-Shuan Huang, Wei-Cheng Liu and Fang-Hsuan Cheng, Taiwan
8-13 Recognition of Lung Cancers on CT Using 3-D Object Models of Different Classes 257
Hotaka Takizawa, Shinji Yamamoto and Tsuyoshi Shiina, Japan
8-14 Model-Based 3D Object Tracking with Online Texture Update 261
Keisuke Tateno, Daisuke Kotake and Shinji Uchiyama, Japan
8-15 On a Technique for Evaluating Performance of Wipers Based on Forward Visibility 265
Takashi Kitayama, Masatoshi Sakai, Takashi Kato, Muneo Yamada, Tomoaki Nakano, Shin Yamamoto, Osami Yamamoto, Masahiko Yamanishi and Hiroshi Matsumoto, Japan
8-16 A Multicamera Vision System Supporting the Development of Wide-Area Exertainment Applications 269
Xenophon Zabulis, Thomas Sarmis, Dimitris Grammenos and Antonis A. Argyros, Greece
8-17 Multiple-Person Tracking for a Mobile Robot Using Stereo 273
Junji Satake and Jun Miura, Japan
8-18 Automatic Analysis of Fish Behaviors and Abnormality Detection 278
Myo Thida, How-Lung Eng and Boon Fong Chew, Singapore
8-19 Video Retrieval System Using Handwriting Sketch 283
Akihiro Sekura and Masashi Toda, Japan
8-20 Linear 3-D Object Pose Estimation with Dense Sample Images –Discussions about Limitation of Parameter Estimation Ability by the Linear Regressions– 287
Toshiyuki Amano and Toru Tamaki, Japan
8-21 Predicting Attainable Region of Vehicle Using Trajectory Clustering 291
Noritaka Sekiyama, Jien Kato and Toyohide Watanabe, Japan
8-22 A Sensor Based Navigation Algorithm for Moving Obstacles Assuring Convergence Property 295
Masaaki Tomita and Motoji Yamamoto, Japan
8-23 Static Estimation of the Meteorological Visibility Distance in Night Fog with Imagery 300
Romain Gallen, Nicolas Hautière and Eric Dumont, France
8-24 Machine Vision for Excess Gluing Inspection in Spindle Motor Assembly 304
Varunyou Buddhachan and Pakorn Kaewtrakulpong, Thailand
8-25 Chromosome Image Recognition with Local Band Patterns 308
Toru Abe, Chieko Hamada and Tetsuo Kinoshita, Japan
8-26 Comparison of Conventional US and Spatial Compound Imaging in Diagnostic Performances of Computer Aided Diagnosis System 312
Wei-Chih Shen, Ruey-Feng Chang and Woo Kyung Moon, Taiwan
8-27 Worker Behavior and Intension Modeling in Production Process 316
Takuma Funahashi, Takayuki Hoshino, Naoya Tokuda, Takayuki Fujiwara and Hiroyasu Koshimizu, Japan
8-28 Investigation of OCT Images Descriptions on the Base of Representational MDL Principle 320
Igor Gurov and Alexey Potapov, Russia
8-29 Feature Level Clustering of Large Biometric Database 324
Hunny Mehrotra, Dakshina R. Kisku, V. Bhawani Radhika, Banshidhar Majhi and Phalguni Gupta, India
8-30 3D Porous Media Liquid-Solid Interaction Simulation Using SPH Modeling and Tomographic Images 328
Alfonso Gastelum Strozzi, Jorge Marquez, Flavio Trujillo, Celine Duwig, Blanca Prado, Pavan Gamage and Patrice Delmas, New Zealand

Session 9: Invited Talk 2

9-1 Focal Stack Photography: High-Performance Photography with a Conventional Camera 332
Prof. Kyros Kutulakos, University of Toronto, Canada

Session 10: Human Sensing

10-1 Shape Measurement System of Foot Sole Surface from Flatbed Scanner Image 338
Sandy Martedi, Hideo Saito and Myriam Servières, Japan
10-2 Extracting Appearance Information inside the Pupil for Cataract Screening 342
Retno Supriyanti, Hitoshi Habe, Masatsugu Kidode and Satoru Nagata, Japan
10-3 Eye Detection Using Intensity and Appearance Information 346
M. Hassaballah and Shun Ido, Japan
10-4 Eye Blink Based Fatigue Detection for Prevention of Computer Vision Syndrome 350
Matjaž Divjak and Horst Bischof, Austria
10-5 Detection of Approaching Pedestrians from a Distance Using Temporal Intensity Patterns 354
Siu-Ming Cheung and Yiu-Sang Moon, Hong Kong

Friday, May 22, 2009

Session 11: Industrial Applications

11-1 A New Flat Pattern Oriented Order Statistic Filter for Impulse Noise Reduction from Highly Corrupted Images 358
Tomohiko Ohtsuka, Homare Sasaki, Masato Suzuki and Hiroyuki Aoki, Japan
11-2 Multiple Object Detection for Pick-and-Place Applications 362
Paolo Piccinini, Andrea Prati and Rita Cucchiara, Italy
11-3 A Cloth Detection Method Based on Image Wrinkle Feature for Daily Assistive Robots 366
Kimitoshi Yamazaki and Masayuki Inaba, Japan
11-4 Carbon Nanotube Detection by Scanning Electron Microscopy 370
Tim Wortmann and Sergej Fatikow, Germany

Session 12: Geographic Information Systems

12-1 Automatic GIS Updating from High Resolution Satellite Images 374
Nicolas Champion, Georges Stamon and Marc Pierrot-Deseilligny, France
12-2 Extracting 3D Polyhedral Building Models from Aerial Images Using a Featureless and Direct Approach 378
Fadi Dornaika and Karim Hammoudi, France
12-3 AR GIS on a Physical Map Based on Map Image Retrieval Using LLAH Tracking 382
Hideaki Uchiyama, Hideo Saito, Myriam Servières and Guillaume Moreau, Japan

Session 13: Poster Session 3

13-1 Probabilistic-Based Semantic Image Feature Using Visual Words 386
Cheng-Chieh Chiang, Jia-Wei Wu and Greg C. Lee, Taiwan
13-2 A Block Matching Technique Using Unit Gradient Vectors 390
Toshiaki Kondo and Waree Kongprawechnon, Thailand
13-3 An Easy Technique for Fisheye Camera Calibration 394
Haijiang Zhu and Fuchao Wu, China
13-4 Robust Vision-Based Target Tracking Control System for an Unmanned Helicopter Using Feature Fusion 398
Feng Lin, Ben M. Chen and Tong H. Lee, Singapore
13-5 Robust Background Segmentation Using Background Models for Surveillance Application 402
Tianci Huang, Jingbang Qiu, Takahiro Sakayori and Takeshi Ikenaga, Japan
13-6 Motion Segmentation Using Divisive Graph Cuts 406
Jong-Sung Kim and Il-Kwon Jeong, South Korea
13-7 A Novel Transducer: From Lip Motion to Voice Message 410
Takeshi Saitoh, Tomoya Kato and Ryosuke Konishi, Japan
13-8 Proposal of Exaggeration Method Based on Shape and Positional Relations of Automotive Parts 414
Hiroshi Fujimoto, Takuma Funahashi, Takayuki Fujiwara and Hiroyasu Koshimizu, Japan
13-9 Image Processing Architecture for Real-Time Micro- and Nanohandling Applications 418
Tim Wortmann, Christian Dahmen, Robert Tunnell and Sergej Fatikow, Germany
13-10 Fitting Curves on Riemannian Manifolds Using Energy Minimization 422
Chafik Samir, Pierre-Antoine Absil, Anuj Srivastava and Eric Klassen, Belgium
13-11 Classification of Spectators' State in Video Sequences by Voting of Facial Expressions and Face Directions 426
Tetsu Matsukawa, Akinori Hidaka and Takio Kurita, Japan
13-12 A Hybrid Model for Multiple Object Category Detection and Localization 431
Dipankar Das, Yoshinori Kobayashi and Yoshinori Kuno, Japan
13-13 Unsupervised Material Classification of Printed Circuit Boards Using Dimension-Reduced Spectral Information 435
Abdelhameed Ibrahim, Shoji Tominaga and Takahiko Horiuchi, Japan
13-14 An Optical Video Cryptosystem with Adaptive Steganography 439
Cheng-Hung Chuang and Guo-Shiang Lin, Taiwan
13-15 Development of System for Comprehensively Measuring Driving Ability for Elderly Safe Driving 443
Toshiaki Kasukabe, Masatake Hiraoka, Osami Yamamoto, Muneo Yamada, Tomoaki Nakano, Shin Yamamoto, Katsumi Matsuda and Mikiko Kawasumi, Japan
13-16 Generation of Overhead View Images by Estimating Intrinsic and Extrinsic Camera Parameters of Multiple Fish-Eye Cameras 447
Ryota Okutsu, Kenji Terabayashi, Yohei Aragaki, Noriko Shimomura and Kazunori Umeda, Japan
13-17 Image Processing in Retinal Angiography: Extracting Angiographical Features without the Requirement of Contrast Agents 451
Tati Rajab Mengko, Astri Handayani, Vanya Vabrina Valindria, Samekta Hadi and Iwan Sovani, Indonesia
13-18 A Human Fall Detection System Using an Omni-Directional Camera in Practical Environments for Health Care Applications 455
Yi-Chang Huang, Shaou-Gang Miaou and Tsung-Yen Liao, Taiwan
13-19 Intrinsic Color Acquisition By Active Color Lighting 459
Hisanaga Fujiwara, Japan
13-20 Large Area Video Surveillance System with Handoff Scheme among Multiple Cameras 463
Cheng-Chang Lien, Yue-Min Jiang and Lih-Guong Jang, Taiwan
13-21 Classification of Wet/Dry Area Based on the Mahalanobis Distance of Feature from Time Space Image Analysis 467
Tomoaki Teshima, Hideo Saito, Masayoshi Shimizu and Akinori Taguchi, Japan
13-22 Classification of In-Vivo Endomicroscopic Images of the Alveolar Respiratory System 471
Caroline Petitjean, Jonathan Benoist, Luc Thiberville, Mathieu Salaün and Laurent Heutte, France
13-23 On Face Recognition Using Hierarchical Self-Organized Gabor Features 475
Saleh Aly, Naoyuki Tsuruta and Rin-ichiro Taniguchi, Japan
13-24 Scallop Detection from Gravel-Seabed Images for Fishery Investigation 479
Koichiro Enomoto, Masashi Toda, Yasuhiro Kuwahara, Masaaki Wada and Katsumori Hatanaka, Japan
13-25 Stereo Vision: A Java-Based Online Platform 483
Minh Nguyen, Georgy Gimel'farb and Patrice Delmas, New Zealand
13-26 Lavatube - A Software Framework for Computer Vision Research and Development 487
Kenji Iwata, Yutaka Satoh and Katsuhiko Sakaue, Japan

Session 14: Invited Talk 3

14-1 Integration of Earth Observation Data: Challenge of GEOSS (Global Earth Observation System of Systems) 491
Prof. Ryosuke Shibasaki, The University of Tokyo, Japan

Session 15: Machine Vision for Transportation

15-1 Automatic Extraction of Droppers in Catenary Scenes 497
Caroline Petitjean, Laurent Heutte, Régis Kouadio and Vincent Delcourt, France
15-2 Free Space Detection for Autonomous Navigation in Daytime Foggy Weather 501
Nicolas Hautière, Jean-Philippe Tarel and Didier Aubert, France
15-3 An Intelligent Night Vision System for Automobiles 505
Tsz-Ho Yu, Yiu-Sang Moon, Jiansheng Chen, Hung-Kwan Fung, Hoi-Fung Ko and Ran Wang, Hong Kong
15-4 A New Approach for In-Vehicle Camera Traffic Sign Detection and Recognition 509
Andrzej Ruta, Yongmin Li, Fatih Porikli, Shintaro Watanabe, Hiroshi Kage and Kazuhiko Sumi, United Kingdom
15-5 Recognition of Road Markings from In-Vehicle Camera Images by a Generative Learning Method 514
Masafumi Noda, Tomokazu Takahashi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, Yoshiko Kojima and Takashi Naito, Japan
15-6 Vision Based Tangent Point Detection Algorithm, Evaluation and Validation 518
Romain Gallen and Sébastien Glaser, France


Author Index 523