MVA 1996: Keio University, Tokyo, Japan

Motion and Focal Plane Architectures

• Vasudevan V. Vinod, Hiroshi Murase:
  Visual Tracking Using Active Search for Color. 1-4
  
• Hichem Sahli, Patrick de Muynck, Jan Cornelis:
  A Kalman Filter-Based Update Scheme for Road Following. 5-9
  
• Dae-Sik Jang, Hyung-Il Choi, Gye-Young Kim:
  Real-time Tracking with Kalman Filter. 10-13
  
• Takayuki Hamamoto, Kiyoharu Aizawa, Mitsutoshi Hatori:
  Video Enhancement Sensor Using Motion Adaptive Storage Time. 14-17
  
• Marius Vasiliu, Francis Devos:
  A Focal Plane Array for Hot Punctual Target Identification and Tracking. 18-21
  

Algorithms

• Christian Küblbeck, Christoph Schittko, Thomas Wagner:
  Automatic Configuration of Systems for Texture Analysis. 22-25
  
• Ming Yu, Shinji Ozawa:
  An Adaptive Threshold Method for Gray Scale Character Images. 26-29
  
• Ali A. Abkar, Nanno J. Mulder:
  A Comparison between Top-Down and Bottom-Up Image Analysis in Terms of the Complexity of Searching a Problem Space. 30-33
  

Poster Session 1

• Pieter Jonker, Eddy Olk, Koen Volker:
  Parallel Image Processing on Heterogeneous SIMD-MIMD Machines. 34-38
  
• Joji Iisaka:
  A Coarse Parallel Image Processing System for Remote Sensing. 39-42
  
• Tomoyuki Hamada:
  A Modularized Vision System Using a Distributed Cooperative Architecture. 43-46
  
• Hiroshi Ueno, Seiji Ishikawa, Yoshinori Otsuka, Kiyoshi Kato:
  Automatic Spinal Deformity Detection by Two Characteristic Axes. 47-50
  
• Kyong-Ho Kim, Sung-Il Chien, Yong-Bum Lee, Kwang-Soo Kim:
  Analog and Digital Meter Recognition Using Computer Vision. 51-54
  
• Yuyo Nogami, Seiji Ishikawa, Kiyoshi Kato:
  A Method of Resolving an Entangled Cord. 55-58
  
• Anders Åström, Erik Åstrand:
  A Compact and High Performance Wood Inspection System Using Smart Sensor Technique and Real-Time Parallel Processing. 59-62
  
• Chunxiao Li, Pingtao Wang, Heitou Zen, Masao Sakauchi:
  Creation of Plane-Spatiotemporal-Image Using a Selected Slit. 63-66
  
• Makoto Kato:
  Interactive Image Segmentation System for Visual Simulation. 67-70
  
• Lampros Tsinas, Volker Graefe:
  Real-Time Recognition of Signaling Lights in Road Traffic. 71-74
  
• Yoshihisa Adachi, Minoru Asada, Takayuki Nakamura:
  Correlation-Based Visual Tracking Enhanced by Affine Motion Description. 75-78
  
• Yi-Bing Yang, H. T. Tsui:
  Position Estimation and Correction of Mobile Robot by Model-based Scene Matching and Optimization Method. 79-82
  
• Aiqun Wang, Nanning Zheng, Lixing Yuan:
  One Dimensional Motion Detector - Multiplicative Inhibitory Velocity Detector (MIVD). 83-86
  
• Zheng Li, Han Wang:
  Model Based Tracking on 3D Objects. 87-90
  
• Kazuyuki Hattori, Yukio Sato:
  Pattern Shift Rangefinding for Accurate Shape Information. 91-94
  
• Takanori Aoi, Hiroshi Nagahashi:
  3-D Modeling from a Single Sketch Image Using Genetic Algorithms. 95-98
  
• Takashi Kobayashi, Osamu Nishimura, Koh Kakusho, Seiichiro Dan, Tadahiro Kitahashi:
  Shape Recovery for Input of a Rough 3D Shape by Its 2D Sketch. 99-102
  
• Nozha Boujemaa, Olivier Montagu, Claude Sourti, Gilles Roux:
  Symbolic Segmentation of Handwritten Numerals with Robust Fuzzy Clustering. 103-106
  
• Yoshihiro Mitani, Yoshihiko Hamamoto, Shingo Tomita:
  Evaluation of the Noise Injection in High Dimensions. 107-110
  
• Hoo Byong Yun, Dong Un An, Seong Jong Chung:
  Region Segmentation of the Color Images for Recognition Based on the Spatial Characteristic and Histogram. 111-114
  
• Zhiyong Yang, Songde Ma, Qifa Ke:
  A New Way to Visual Representation and Learning. 115-118
  
• Megumi Kawata, Jack Koplowitz, Masato Sakata:
  A Study on Subpixel Smoothing for Binary Images. 119-122
  
• Fumihiko Saitoh:
  Components Recognition by the Generalized Hough Transform Using Multiple Two-dimensional Parameter Spaces. 123-126
  
• Toshinori Hayashi, Yuzuru Tanaka:
  Image Features Based on a Mixed Fractal Model and Evaluation of Their Effectiveness in Image Retrieval. 127-130
  
• Lin Yu Tseng, Rung Ching Chen:
  An Efficient Recognition and Data Extraction Method for Table-Form Documents. 131-134
  
• Takayuki Kondo, Kazuhito Murakami, Hiroyasu Koshimizu:
  On a Simple Method for Corresponding 3-D Facial Images and Its Application to Generate Facial Caricature. 135-138
  
• Hiroshi Shinjo, Kazuki Nakashima, Masashi Koga, Katsumi Marukawa, Yoshihiro Shima, Eiichi Hadano:
  A Connecting Method for Disappeared Corner Patterns in Form Documents. 139-142
  
• Kazuki Nakashima, Masashi Koga, Katsumi Marukawa, Yoshihiro Shima:
  A Restoration Method for Broken Handwritten Line-figures with Connecting Terminal Points. 143-146
  
• Masakazu Nishijima, Toyohide Watanabe:
  An Automatic Extraction of Road Information on the Basis of Cooperative Hypotheses Interpretation Mechanism. 147-150
  

Invited Talk 1

• Thien M. Ha, Horst Bunke, Guido Kaufmann:
  Perturbation Models: A New Approach to Improving Handwriting Recognition. 151-159
  

Architectures

• Sholin Kyo, Kan Sato:
  Efficient Implementation of Image Processing Algorithms on Linear Processor Arrays Using the Data Parallel Language IDC. 160-165
  
• Eril Mozef, Serge Weber, Jamal Jaber, Claude Bataille:
  LAPCAM, Linear Array of Processors Using Content-Addressable Memories: A New Design of Machine Vision for Parallel Image Computations. 166-169
  
• Yoshihiro Fujita, Nobuyuki Yamashita, Shin'ichiro Okazaki:
  IMAP-VISION: An SIMD Processor with High-Speed On-chip Memory and Large Capacity External Memory. 170-173
  
• Yudi Yanuhardi, Trio Adiono, Tati Rajab Mengko:
  TMP5X5T1M: A Configurable Binary Morphological and Template Matching Processor. 174-177
  
• Mahmoud Meribout, Takeshi Ogura, Mamoru Nakanishi:
  Real-time Hough Transform Based Circular Shape Extraction. 178-182
  

Applications 1

• Massimiliano Loria, Alberto Machì:
  Automatic Visual Control of a Pedestrian Traffic Light. 183-186
  
• Kentaro Hayashi, Yoshinori Kuno, Yoshiaki Shirai:
  Human-Robot Interface with Appropriate Frame Selection. 187-190
  
• Yasuhiko Watanabe, Yoshihiro Okada, Tatsuhiko Tsunoda, Makoto Nagao:
  Aligning Articles in TV Newscasts and Newspapers. 191-195
  
• Ebroul Izquierdo, Michael Karl:
  Low Complexity Disparity Estimation and Object-Based Image Synthesis for Multi-Viewpoint Stereoscopic Videoconferencing. 196-199
  
• Keith J. Hanna, Robert Mandelbaum, Deepam Mishra, Vince Paragano, Lambert E. Wixson:
  A System for Non-Intrusive Human Iris Acquisition and Identification. 200-203
  
• Joachim Denzler, Heinrich Niemann:
  3D Data Driven Prediction for Active Contour Models with Application to Car Tracking. 204-207
  
• Toshikazu Wada, Takekazu Kato:
  Event Driven Motion-Image Classification by Selective Attention Model. 208-211
  
• Wlodzimierz Kasprzak, Heinrich Niemann:
  Applying a Dynamic Recognition Scheme for Vehicle Recognition in Many Object Traffic Scenes. 212-215
  
• Antonis A. Argyros, Manolis I. A. Lourakis, Panos E. Trahanias, Stelios C. Orphanoudakis:
  Fast Visual Detection of Changes in 3D Motion. 216-219
  
• Masafumi Tominaga, Kunihito Kato, Kazuhito Murakami, Hiroyasu Koshimizu:
  Realization of Askant Glance Camera Vision System by Using Extended Hough Transform. 220-224
  

Poster Session 2

• G. M. T. Cross, Roberto Cipolla:
  Affine Contour-Based Visual Servoing. 225-228
  
• Ying-Jieh Huang, Hiroshi Dohi, Mitsuru Ishizuka:
  A Vision System with Dual Viewing Angles for Spontaneous Speech Dialogue Environment. 229-232
  
• Zhongchao Shi, Ryosuke Shibasaki:
  An Approach to Automated House Recognition from Digital Stereo Imagery. 233-236
  
• Oliver Dehning, Claus-E. Liedtke:
  Gipsy: Knowledge Based Surface Inspection. 237-240
  
• Takafumi Hara, Tomoyuki Kudou, Eturo Yokoyama, Hidetoshi Miike, Atsushi Nomura:
  Recovering 3D-Shape from Motion Stereo under Non-Uniform Illumination - A Vision System for Mobile Robot Carring an Illumination Source -. 241-244
  
• Kazuya Takahashi, Tadaaki Kitamura, Masao Takatoo, Yoshiki Kobayashi, Yoshiyuki Satoh:
  Traffic Flow Measuring System by Image Processing. 245-248
  
• Georges Quénot:
  Computation of Optical Flow Using Dynamic Programming. 249-252
  
• Ping Xiao, Maylor K. H. Leung, Kok Cheong Wong:
  Eleview: An Active Elevator Monitoring Vision System. , . 253-256
  
• Kayoko Kitai:
  A Study of Automatically Tracking Pedestrian Flow. 257-260
  
• Toshifumi Honda, Yukio Matsuyama, Hisae Yamamura, Hideaki Sasazawa, Takanori Ninomiya, Ludwig Listl, Anton Schick, Richard Schneider:
  Automated Visual Inspection Algorithm for Solder Joint of Surface Mount Devices Based on Three Dimensional Shape Analysis. 261-266
  
• Erik R. van Dop, Paul P. L. Regtien:
  Object Recognition from Range Images Using Superquadric Representations. 267-270
  
• Dmitry Langumovsky, Sergey Ablameyko, M. Kutas:
  Extraction of Topological Features of Integrated Circuit from Grey-Scale Image. 271-274
  
• Yasuo Yoshida, Yue Wu:
  Classification of Rotated and Scaled Textured Images Using Spectral Moments. 275-278
  
• Shan Jiang, Yufang Sun:
  Dynamic Feature in Complicated Pattern Recognition. 279-284
  
• Ivá Valdés, Yoshihiko Nomura, Yasunaga Mitsuya:
  Equidistant Snakes: Accurate Irregular Shaped Contour Detection. 285-288
  
• Ichiro Murase, Shun'ichi Kaneko, Satoru Igarashi:
  Inductive Learning of Primitive Shape Features of Closed Contours. 289-292
  
• Masaki Otsuki, Yukio Sato:
  Highlight Separation Using Multiple Images with Intensities and Ranges.. 293-296
  
• Hitoshi Saji:
  Measuring Three-Dimensional Shapes of a Human Face Using Photometric Stereo Method with Two Light Sources and Slit Patterns. 297-300
  
• Tae Wan Choi, DaeHyun Ryu, Jae-Chang Kim:
  Implementation of an Orientation Selective Hierarchical Spatial Filter Using Diffusion Network. 301-304
  
• Phongsuphap Sukanya, Ryo Takamatsu, Makoto Sato:
  Texture Classification Based on Topographic Image Structure. 305-308
  
• Xavier Cufí, Alicia Casals:
  A Criterion for Circumscribed Contours Determination for Image Segmentation. 309-312
  
• Yoshiaki Kuno, Tohru Yagi, Yoshiki Uchikawa:
  A Wide-View VR System with Multi-Level Description and Rendering of 3D Scenes. 313-316
  
• Yuichi Murai, Kazumasa Bansho, Ken-Ichi Noda:
  Pitched Baseball Image Extraction in Natural Color TV Scene and Its Trajectory Pursuit. 317-320
  
• Kenji Terada, Masaki Fujikawa, Jun-Ichi Yamaguchi:
  An Automatic Method of Counting the Passing People through the Gate by Using Two Space-time Images. 321-324
  
• Yoshihiro Kawai, Fumiaki Tomita:
  A Support System for the Visually Disabled to Recognize 3D Objects. 325-328
  
• Hiroshi Mo, Shin'ichi Satoh, Masao Sakauchi:
  A New Type of Video Scene Classification System Based on Typical Model Database. 329-332
  
• Han Wang, Stan Z. Li, S. Ragupathi:
  A Fast and Robust Approach for Document Segmentation and Classification. 333-336
  
• Qifa Ke, Jing Xiao, Zhiyong Yang:
  Energy-based Method for Road Extraction from Satellite Images. 337-340
  
• Souad Tayeb-bey, Alexandre S. Saidi, Hubert Emptoz:
  Grammatical Approach for the Physical and Logical Structure of Documents Analysis; Application to Summary Documents. 341-343
  
• Yining Ou, Jianqi Huang, Yinglin Yu:
  A Practical Data Compression System for Map Images. 344-347
  
• Naoko Yokokura, Toyohide Watanabe:
  Recognition of Composite Elements in Bar Graphs. 348-351
  

Invited Talk 2

• Gérard G. Medioni:
  Using Computer Vision in Real Applications: Two Success Stories, . 352-360
  

Documents and Maps

• Paul C. K. Kwok, Lok C. Wong:
  Run-time Behavior of Contour Tracing Algorithms for Document Conversion. 361-364
  
• Chang-Heon Woo, Soo Yong Kim, Sung-Nam Oh:
  A New Method for Extracting Map Elements by Their Colors and Shapes from Color Cartographic Maps. 365-368
  
• Hiroyuki Masai, Toyohide Watanabe:
  Identification of Document Types from Various Kinds of Document Images Based on Physical and Layout Features. 369-372
  
• Gerd Maderlechner, Thomas Brückner, Peter Suda:
  IDA: A System for Automated Sorting, Indexing, and Classification of Documents. 373-376
  
• Jean-Luc Henry, Frank Lebourgeois:
  Cooperation between Patterns Recognition and Contextual Analysis: Application to the Reading of Printed Documents. 377-380
  

Shape

• Atsushi Sakai, Yoshihiko Nomura, Yasunaga Mitsuya:
  Matching for Affine Transformed Pictures Using Hough Planes. 381-384
  
• Ge Cong, Songde Ma:
  Planar Shape Enhancement by General Geometric Heat Flow. 385-388
  
• Massimo De Gregorio:
  Is That Portal Ghotic? A Hybrid System for Recognising Architectural Portal Shapes. 389-392
  
• Iman Triono, Kenichi Kanatani:
  Automatic Recognition of Regular Figures by Geometric AIC. 393-396
  

3D

• Anders Åström, Erik Åstrand:
  Very High Speed Multi Resolution Sheet-of-light Range Imaging. 397-400
  
• Il Dong Yun, Ja Seong Ku, Sang Uk Lee:
  Inspection of Shiny Surface Using a Laser Range Finder. 401-405
  
• Ikuko Shimizu, Koichiro Deguchi:
  A Method to Register Multiple Range Images from Unknown Viewing Directions. 406-409
  
• Pingtao Wang, Chunxiao Li, Heitou Zen, Masao Sakauchi:
  3D Information Acquisition from Plane Spatio-Temporal Images with Complicated Camera Motion. 410-413
  
• Jaap Glas, Ferdinand van der Heijden:
  A Radiometric Noise Model for Estimating Geometrical Parameters of 3-D Bodies from Multispectral Images. 414-417
  

Poster Session 3

• Kiyoharu Aizawa, Y. Egi, Takayuki Hamamoto, Yasuhiro Ohtsuka, Mitsutoshi Hatori, H. Maruyama, M. Abe:
  Focal Plane Compression Sensors Based on Pixel Parallel and Column Parallel Architectures. 418-421
  
• Gunter Magin, Christian Robl, Georg Färber:
  A Single Processor Realtime Edge-Line Extraction System for Feature Tracking. 422-425
  
• Yutaka Nagashima, Takeshi Nakazono, Takakazu Ishimatsu:
  Parallel Implementation of Features Extraction Using Morphological Filter. 426-429
  
• Eiichi Hosoya, Takeshi Ogura, Mamoru Nakanishi:
  Real-time 3D Feature Extraction Hardware Algorithm with Feature Point Matching Capability. 430-433
  
• Antonio Jose Garrido del Solo, Pedro Cuenca, Francisco J. Quiles, Teresa Olivares:
  Utilization of Network-Based Multicomputer with ATM Technology in Digital linage Processing Applications. . .. 434-437
  
• Yasuhiro Fujimura, Akira Kawanaka, Hideki Hayakawa:
  Estimating the Propagation Velocity Distribution and the Position of Buried Pipe Using x -t - v Data Matrix of Subsurface Radar Image. 438-443
  
• Hiroki Nakano, Yasuo Yoshida:
  Detection and Visualization of Macro Defects of Color Liquid Crystal Display through Gabor Transform. 444-449
  
• Kazuaki Nakamura, Jiang Hao, Shinji Yamamoto, Tetsuya Itoh:
  Document Image Segmentation into Text, Continuous-Tone and Screened-Halftone Region by the Neural Networks. 450-453
  
• Yasukazu Okamoto, Sakae Kusakabe, Hitoshi Hata:
  Train Wheel Abrasion, Measurement Method Using Contour Information. 454-457
  
• Wei-Yun Yau, Han Wang, Dinesh P. Mital:
  Hand-Eye Coordination Using Active Stereo Camera. 458-461
  
• Eiji Takahashi, Hirohumi Terada, Yoshiro Nishimoto, Yuichiro Goto, Akashi Yamaguchi, Hideki Yamamuro, Atushi Miyawaki, Masami Fujii, Makoto Nakamura:
  Automatic Visual Inspection System for Tape Carrier Package Using Unique Image Processing and Human Visual Support. 462-465
  
• Yuichi Tamura, Ken Hashimoto, Hiroshi Kohda, Yasuji Hattori:
  Measurement of Displacement of Optical Fiber Using Light Intersection Method. 466-469
  
• Lixu Gu, Naoki Tanaka, Robert M. Haralick, Toyohisa Kaneko:
  The Extraction of Characters from Scene Image Using Mathematical Morphology. 470-473
  
• Tetsuya Takeda, Yoshihiro Okada:
  Feature Extraction and Description from Image Based on Isochromatic Information. 474-477
  
• Eric Duquenoy, Abdelmalik Taleb-Ahmed, Yves Beral:
  A New Approach for Modelisation of Ellipsoidal-based Shape. 478-481
  
• Zhiyong Yang, Songde Ma, Qifa Ke:
  MDL Mediated by Geometrical Redundancy Reduction and Complement Space. 482-485
  
• Keiichi Yamada, Morimichi Mizuno, Toshihiko Tsukada, Shin Yamamoto:
  A Robust Vision System against the Change of Lighting Condition. 486-489
  
• Stephen Wang-Cheung Lam:
  A Relaxed Fuzzy ISODATA Algorithm. 490-493
  
• N. V. Subba Reddy, P. Nagabhushan:
  A Neural Network Based Multiple Expert System Model for Conflict Resolution. 494-497
  
• Osamu Shiku, Akira Nakamura, Hideaki Takahira, Hideo Kuroda:
  A Method for Character String Extraction from Binary Images Using Hough Transform. 498-501
  
• Sergey Ablameyko, Maria Frucci, Angelo Marcelli:
  Extracting Shape Primitives from Skeleton. 502-505
  
• Wei Wu, Hiroshi Mo, Masao Sakauchi:
  An Image Retrieving System Based on User-Specified Recognition Model. 506-509
  
• Jean Michel Marie-Julie, Hassane Essafi:
  Fast Parallel Multimedia Database Access Based on Wavelet Multiresoliition Pyramidal Decomposition. 510-513
  
• Gang Wang, Yijia Lin, Yueyue Song:
  The Vectorization of Engineering Drawings Based on Statistics. 514-517
  
• Kyung-Ae Moon, Hyung Lee, Hee-Jun Yoon, Jong-Won Park:
  A Parallel Processing System for a High-Speed Printed Document Recognition. 518-521
  
• Tsuneo Sobue, Toyohide Watanabe:
  Identification of Item Fields in Table-form Documents with/without Line Segments. 522-525
  
• Kimihiro Uno, Hidetoshi Miike:
  A Stereo Vision through Creating a Virtual Image Using Affine Transformation. 526-529
  
• Atsuto Maki, Tomas Uhlin, Jan-Olof Eklundh:
  A Direct Disparity Estimation Technique for Depth Segmentation. 530-533
  
• Takashi Yoshimi, Yoshihiro Kawai, Fumiaki Tomita:
  Range Data Segmentation with Principal Vectors and Surface Types. 534-537
  
• X. Y. Jiang, Horst Bunke:
  Robust and Fast Edge Detection and Description in Range Images. 538-541
  

Invited Talk 3

• Marco Ferretti, Maria Grazia Albanesi:
  Architectures for the Hough Transform: A Survey.. 542-551
  

Application 2

• Petra Perner:
  Ultra Sonic Image Interpretation for Non-Destructive Testing. 552-554
  
• S. C. Li, C. K. Lee:
  Matching of IC Patterns under Non-Uniform Illumination. 555-558
  
• Itqon, Shun'ichi Kaneko, Hidefumi Kobatake, Fumio Otsuki, Hideyuki Tanaka, Mitsunori Murata:
  Analysis of Bone Shape by Local Controlled Deformable Contour for Bone Maturity Estimation. 559-562
  
• G. M. T. Cross, Roberto Cipolla:
  Automated Weld Tracking. 563-565
  
• Ryan Raz:
  Design of the Cymet A40 Pap Test Prescreener. 566-569