(IAPR MVA '92)

December 7-9, 1992, Minato-ku, Tokyo, Japan

Table of Contents

Front Messages in the Proceedings


New Architectures for Vision (Invited) 1
Kendall Preston, Jr. , Kensal Consulting, USA
A Low-Cost Parallel VLSI Architecture for Low-Level Vision 11
Alberto Broggi', Vincenzo D'Andrea* and Francesco Gregoretti**, *Universita di Parma, **Politecnico di Torino, Italy
MAPP2200 Smart Vision Sensor. Prog‚’ammability and Adaptivity 17
Anders Aström and Robert Forchheimer, Linköping University, Sweden
The Versatile Image Processor V. I. P. (Hardware Design) 21
G. Gugliotta and A. Machi, IFCAI, Italy

3D Object Recognition

Estimating Surface and Spatial Structure from Wire-Frame Model Using Geometrical & Heuristical Relation 25
Akira Utsumi, Yasushi Yagi and Masahiko Yachida, Osaka University, Japan
View-Based Recognition 29
Thomas M. Breuel, IDIAP, Switzerland
Recognising Objects with Variable Appearances Using the VAPOR Model 33
John Canning, NTT, Japan
A Hybrid Approach towards Segmentation of Range Images 39
Alan Wui Tze Lim, Earn Khwang Teoh and Dinesh P. Mital, Nanyang Technological University, Singapore
An Image Sensor for Sheet-of-Light Range Imaging 43
Mattias Johannesson, Anders Aström and Per-Erik Danielsson, Linköping University, Sweden

Poster Session 1

A Real-Time Vision System Using Integrated Memory Array Processor Prototype LSI 47
Yoshihiro Fujita, Nobuyuki Yamashita and Shin'ichiro Okazaki, NEC, Japan
An Host-Target Environment for Real Time Image Processing 51
M. Pizzocaro, Blaise Pascal University, France
VLSI Optimal Edge Detection Chip: Canny-Deriche Filter 55
Mohamed Akil and Nizar Zarka, Laboratoire I. A. A. I., France
Fast Raster-to-Vector Conversion of Large-Size 2d Line-Drawings in a Restricted Computer Memory 59
S. Ablameyko, V. Bereishik, O. Frantskevitch, M. Homenko, E. Melnik and N. Paramonova, Belarusian Academy of Sciences, Belarus
Extraction of Color Region Boundaries 63
Stephen M. Blackburn, Australian National University, Australia
Region-Based Top-Down Segmentation Controlled by Stereo Matching 67
Sabine Randriamasy and André Gagalowicz, INRIA, Rocquencourt, France
Separation of Textual and Non-textual Information within Mixed-Mode Documents 71
Frank Hoenes and Rainer Zimmer, German Research Center for Artificial Intelligence, Germany
Representing and Utilising Knowledge for Understanding Structured Documents 75
Thomas Bayer, Daimler-Benz, Germany
Structure Recognition of Table-Form Documents on the Basis of the Automatic Acqusition of Layout Knowledge 79
Qin Luo, Toyohide Watanabe and Noboru Sugie, Nagoya University, Japan
An OCR System for Printed Documents 83
F. Lebourgeois, J. L. Henry and H. Emptoz, Institut National des Sciences Appliquées de Lyon, France
Contour Map Reconstruction via Multi-Module Parallel Computational Scheme 87
Miyuki Kawashima, Ryuji Tokunaga and Yuzo Hirai, University of Tsukuba, Japan
Neural Networks Applied to Recognition of CCD Camera Images where a 3-Digit Number is Stamped on the Surface of Chip Resistors 93
Katsuji Imai*, Kazutoshi Gouhara** and Yoshiki Uchikawa**, *Toyota Motor Corp. , **Nagoya University, Japan
Recognition of Raised Characters for Rubber Tires Classification 97
Min Seok Rang*, Young Kug Ham*, Hong Kyu Chung*, Rae-Hong Park* and Gwi-Tae Park**, *Sogang University, **Korea University, Korea
Image Sequence Analysis Using Color Multiplex Image 101
Yoshitomo Yaginuma and Masao Sakauchi, University of Tokyo, Japan
Robust Estimation of Focus of Expansion and Depth from High Confidence Optical Flow 105
Sanbao Xu and Per-Erik Danielsson, Linköping University, Sweden
Long Image Sequence Motion Analysis Using Polynomial Motion Models 109
Xiaoping Hu and Narendra Ahuja, University of Illinois, USA
Full-Passive Human Recognition from Image Sequences 115
Satoshi Abe*, Koji Nakamura*, Mamoru Maekawa* , Takanobu Endo* and Nobuyuki Sugiura*, University of Tokyo, **University of Electro-Communications, Japan
Proposition of a Human Motion Tracking Method by Temporal-Spatial Segmentation in an Image Sequence 119
Frédéric Elsner, Khaled Hacine, Naceur Kerkeni, Jean-Claude Angué and Michel Bourton, Université de Valenciennes, France
A New Perceptual Approach to Noisy X-Ray Image Segmentation 123
Jian-qin Liu, Nan-ning Zheng and Xu-dong Guan, Xian Jiaotong University, PRC
Segmentation of T1-, T2-, and PD-Weighted MR Images 129
Manuela Schäfer, Dinu Scheppelmann, Uwe Engelmann and Hans-Peter Meinzer, German Cancer Research Center, Germany
A Method for Tumor Shape Extraction from X-Ray Mammography 133
Yoichi Takeshita, Mutsuhiro Terauchi and Kenji Onaga, Hiroshima University, Japan
A Hierarchical Determination of Optimal Camera and Light-Source Positions for Model-Based Recognition 137
Shinichiro Gomi and Koichiro Deguchi, University of Tokyo, Japan
A Multiscale Analysis Model Applied to Natural Surfaces 141
Frédéric Falzon, Gérard Giraudon and Marc Berthod, INRIA, Sophia-Antipolis, France
Object Recognition Using Temporal Pattern Recognition Networks with Adaptive Segmentation of Quantizer Neuron Architecture (TASQA) 145
Susumu Maruno*, Chow Yuet Dih**, Yasuharu Shimeki*, Takashi Anezaki* and Yoshikazu Okahashi*. *Matsushita Elec. Ind. Co. , Ltd. , Japan, **Asia Matsushita Electric (S) Pte. Ltd. , Singapore
Generating Hierarchical Aspect Graph Using Silhouettes of Curved Objects 149
Satoru Morita, Toshio Kawashima and Yoshinao Aoki, Hokkaido University, Japan
Invariant Object Recognition Using Neural Network Ensemble on the CM 153
Daijin Kim* and Minsoo Suk**, *Dong-A University, Korea, **Syracuse University, USA
Neural Network Approaches for Attractive Area Extraction from Video Images 159
Jun Ogata*, Mikiya Sase** and Yukio Kosugi**, *Toshiba Corp. , **Tokyo Institute of Technology, Japan
An Extraction Method of Search Indexes for Graph Image Retrieval 163
Masashi Koga, Tatsuya Murakami, Yoshihiro Shima and Hiromichi Fujisawa, Hitachi, Ltd. , Japan
Cylindrical Object Reconstruction with a Moving Camera Embedded in a *Poor* robotic platform 167
Marc Viala*, Christian Faye**, Jean-Pierre Guerin* and Didier Juvin*, *LETI, **ENSEA, France
Representation and Reconstruction of Three-Dimensional Objects Using Nonlinear Deformable Superquadric Models 171
Chao Zhang and Baozong Yuan, Northern Jiaotong University, PRC
Determining Surface Roughness and Shape of Specular Diffuse Lobe Objects Using Photometric Sampling Device 175
Tetsuo Kiuchi and Katsushi Ikeuchi, Carnegie Mellon University, USA
A Texture Based Shape Connection Method for 3-D Shape Reconstruction 179
Makoto Maruya, Keiji Nemoto and Yosuke Takashima, NEC, Japan
Theoretical Analysis of Scanning Electron Microscopes with Plural Detectors as an Application Field of Photometric Stereo 183
Makoto Kato, Hitachi, Ltd. , Japan

Motion & Navigation

Effective Vision Algorithms for Detection of Structured and Unstructured Roads 187
Lampros Tsimas and Feiyu Liu, Universität der Bundeswehr München, Germany
A Complete Navigation System for a Mobile Robot, Using Real-Time Stereovision and the Delaunay Triangulation 191
Michel Buffa, Olivier D. Faugeras and Zhengyou Zhang, INRIA, Sophia-Antipolis, France
A Mobile Robot for Visual Measurements in Architectural Applications 195
Xavier Lebègue and J. K. Aggarwal, University of Texas at Austin, USA
A Fast Object Flow Estimation Method Based on Spacetime Image Analysis 199
Kenji Mase, Atsushi Sato, Yasuhito Suenaga and Kenichiro Ishii, NTT, Japan
Finding Spatio-Temporal Contour of Moving Objects 203
Kenji Nagao*, Masaki Sohma*, Katsura Kawakami*, Michihiro Kobayakawa* and Shigeru Ando**, *Matsushita Industrial Co. , Ltd. , **University of Tokyo, Japan
Estimation and Interpretation of Optical Flow Fields for Counting Moving Objects 209
Alberto Del Bimbo*, Paolo Nesi*'** and Jorge L. C. Sanz**'***, *University of Florence, Italy, **IBM, USA, ***IBM, Argentina

Image Processing & Algorithm

Background Image Generation by Cooperative Parallel Processing Under Severe Outdoor Condition 215
Katsunori Inoue and Wonchan Seo, Osaka Univ. , Japan
Character Extraction from Gray Images Based on Mathematical Morphology 219
Yasuko Takahashi, Akio Shio and Kenichiro Ishii, NTT, Japan
High Speed Autofocus for Microscopic Images 223
J. E. Fischer*, D. Homeister*, J. Lehmler* and G. Roos**, University of Stuttgart, **Institute for Microelectronics Stuttgart, Germany
Adaptive Image Sharpening Method Using Edge Sharpness 227
Akira Inoue and Johji Tajima, NEC, Japan
An Experiment of Realization of Fully Automated Keyword Extraction in Image Database System 231
Jun Yamane and Masao Sakauchi, University of Tokyo, Japan
Contour Based Image Segmentation Process on a Parallel Vision Machine 235
Pascal Legrand and Jean Pierre Derutin, Blaise Pascal University, France

Poster Session 2

Massively Parallel Image Segmentation on the Connection Machine 241
M. Berthod*, G. Giraudon* and J. P. Stromboni*, *INRIA, Sophia-Antipolis, **Université de Nice Sophia Antipolis, France
Morphological Algorithms Adapted to a Linear Acquisition 245
A. Amorouayeche, Universite de Valenciennes et du Hainaut Cambrésis, France
Permanence Memory: A System for Real Time Motion Analysis in Image Sequences 249
Miguel A. Fernández* and J. Mira**, *Universidad de Castilla la Mancha, **Faculted de Ciencias Fisicas de la U. N. E. D. , Spain
The Programmable and Configurable Low Level Vision Unit of the HERMIA Machine 253
G. Gerardi* and G. Parodi**, *Univ. Palerno, **Univ. Genova, Italy
The Domain of Orthogonal Transforms and the Understanding of Image Features 257
Malek Adjouadi, Habibie Sumargo, Jean Andrian and Frank Candocia, Florida International University, USA
Towards a Versatile Framework for Intermediate-Level Computer Vision 261
Luciano da Fontoura Costa, Univ. de S. Paulo, Brazil
A Multi-Scale Regularity Measure as Geometric Criterion for Image Segmentation 265
Bruno Vassele and Gérard Giraudon, INRIA, Sophia-Antipolis, France
A New Parallel Scheme for Robust Segmentation of Textured Images 269
Xu-dong Guan, Jian-qin Liu and Nan-ning Zheng, Xian Jiaotong University, PRC
A Parallel Topological Map for Image Segmentation 273
Dinu Scheppelmann, Jochen Frey, Manuela Schäfer and Hans-Peter Meinzer, German Cancer Research Center, Germany
Measurement of Enzymatic Treatment Effect on Textile Using Digital Image Analysis 277
J. Michael Carstensen, Michael Grunkin and Knut Conradsen, Technical University of Denmark, Denmark
Texture Classification by Wavelet Packet Signatures 281
Andrew Laine and Jian Fan, University of Florida, USA
Hierarchical Recognition of Mixed Documents Consisting of the Korean/Alphanumeric Texts and Graphic Images 287
Young Kug Ham*, Hong Kyu Chung*, In Kwon Kim*, Rae-Hong Park*, Chang Bum Lee**, Sang Joong Kim** and Byeong Nam Yoon**, *Sogang University, **Electronics and Telecommunications Research Institute, Korea
Hybrid Structured Dictionary for Improving Text Recognition 291
Rainer Hoch, German Research Center for Artificial Intelligence, Germany
A Syntactical Approach to the Database Construction Method from Document Images 295
Atsuhiro Takasu, Shin'ichi Satoh and Eishi Katsura, National Center for Science Information Systems, Japan
An Al-Aided System for the Conversion of Paper-Based Technical Drawings into a CAD Format 299
J. M. Gloger*, B. Pasternak**, R. Sprengel**, G. Gabrielides**, N. Luth*** and M. Timmermann***, *Daimler Benz, **University of Hamburg, ***Instiiute for Production Systems and Design Technology, Germany
Error Correction for Recognition of Handwritten Kanji Names Using a Name Knowledge Base 303
Katsumi Marukawa, Masashi Koga, Yoshihiro Shima and Hiromichi Fujisawa, Hitachi, Ltd. , Japan
Design of a Fuzzy Inspection and Recognition System for Binary Image 309
Bin-Yih Liao*'** and Ming-Shing Young**, *National Kaohsiung Institute of Technology, **National Cheng-Kung University, ROC
Structure from Motion Using Coarse to Fine 3d Voting 313
Weiming Yao, Tsutomu Horikoshi, Takayuki Yasuno and Satoshi Suzuki, NTT, Japan
Target Tracking from Binocular Image Sequence Using the Autoregressive Moving Average Model 317
Zhen Hong and Narendra Ahuja, University of Illinois, USA
Tracking of Vehicles at an Intersection by Integration of Multiple Image Sensors 321
Shuichi Nishio* and Yuichi Ohta**, *NTT Data Communications Systems Corp. , **University of Tsukuba, Japan
Cloudy Sky Velocity Map Based on Matched Filter 325
C. Collet*, A. Quinquis* and J. M. Boucher**, *Ecole Navale, **ENSTBr, France
A Vision Based Control Approach to High Speed Automatic Vehicle Guidance 329
Frederic Jurie*, Patrick Rives**, Jean Gallice* and Jean-Luc Brame***, *Blaise Pascal University, **INRIA, Sophia-Antipolis, ***P. S. A. Peugeot Citroën, France
Depth Independent Facial Movement Estimation 335
Haibo Li and Robert Forchheimer, Linköping University, Sweden
Sign Language Translation System Using Continuous DP Matching 339
Hirohiko Sagawa, Hiroshi Sakou and Masahiro Abe, Hitachi, Ltd. , Japan
A Measuring System for Traffic Flow of Passers-by by Processing ITV Image in Real Time 343
Hideo Tamamoto*, Yuichi Narita*, Akira Yanase**, Futoshi Saito*** and Kazuto Komatsu**`*, *Akita University, **Odate Technical High School, ***Goyo Electronics Co. , Ltd. , ****Ricoh System Development Co. , Ltd. , Japan
A Proposal of a Multimedia Cooperative Drama Scene Recognition System 349
Yoshitomo Yaginuma and Masao Sakauchi, University of Tokyo, Japan
Image Processing Method for Intruder Detection around Power Line Towers 353
Masahisa Kaneta*, Hitoshi Kanoh*, Kimiharu Kanemaru* and Toshio Nagai**, *Hitachi Cable, Ltd. , **Kansai Electric Power Co. , Inc. , Japan
Under the Sun Light. From Physics to Image Processing 357
B. Collin* and B. Zavidovique**, *ETCA/CREA/SP, **Univ. de Paris-Sud Orsay, France
Satellite Image Processing Using Cellular Array Processor(CAP) 363
Masataka Ajiro*, Hiroyuki Miyata**, Takashi Kan** and Makoto Ono**, *ERSDAC Data Center, **Mitsubishi Electric Corporation, Japan
Segmentation of Color Aerial Photographs Using HSV Color Models 367
Daisuke Yagi, Keiichi Abe and Hiromasa Nakatani, Shizuoka University, Japan
Model Based Object Recognition Using Modified Coded Boundary Representation (MCBR) Method 371
Katsunori Inoue*, Shuichi Fukuda**, Masashi Okubo* and Tong Qin***, *Osaka University, **Tokyo Metropolitan Institute of Technology, Japan, ***Harbin Institute of Technology, PRC
An Interactive 3d Symmetry Analysis System 375
Seiji Ishikawa*, Keiichi Sato*, Predrag Minovic** and Kiyoshi Kato*, *Kyushu Institute of Technology, **SECOM Co. Ltd. , Japan
Stereo Matching Based on Iterative Incompatibility Revision 379
Yasuo Seki and Hisayuki Tatsumi, Kanagawa Institute of Technology, Japan
Correspondence of Surfaces in a Sequence of Range Images for Motion Estimation and Tracking 385
Bikash Sabata and J. K. Aggarwal, University of Texas at Austin, USA
Computation of Surface Curvature from Range Images Using Geometrically Intrinsic Weights 389
Takio Kurita* and Pierre Boulanger**, *Electrotechnical Laboratory, Japan, **National Research Council Canada, Canada

Map & Drawing

Technical Drawing Recognition and Understanding: From Pixels to Semantics (Invited) 393
Karl Tombre, INRIA, Lorraine, France
Data Conversion for GIS 403
Peter Mowforth, The Turing Institute Ltd. , UK
Understanding Rule Generation Supporting System for Drawing Understanding using Interaction with User 407
Shin'ichi Satoh* and Masao Sakauchi**, *National Center for Science Information Systems, **University of Tokyo, Japan
Primitive Extraction Using Incremental Curve Generation 411
Gerhard Roth, National Research Council of Canada, Canada

Applications 1

Practical Considerations about a 2d Algorithm for Object Orientation in Industrial Applications 415
Curt L. Orbert, Ewert W. Bengtsson and Bo G. Nordin, Uppsala University, Sweden
Automated Inspection of Printed Circuit Board Patterns Referenced to CAD Data 419
Hideaki Doi*, Yasuhiko Hara*, Koichi Karasaki*, Tadashi Iida*, Takashi Furutani** , Shigeki Kitamura**, Norihiro Minatani** and Satashi Shinada**, *Hitacki, Ltd. , **Hitachi Video and Information System, Inc. , Japan
Detection and Discrimination of Surface Defects by Analyzing Diffraction Pattern of Laser Beam 425
Saburo Okada*, Masaaki Imade*, Hidekazu Miyauchi*, Tetsuhiro Sumimoto** and Hideki Yamamoto***, Government Industrial Research Institute, Chugoku, **Maritime Safety Academy, ***Okayama University, Japan
Development of Solder Joint Inspection Method Using Air Stimulation Speckle Vibration Detection Method and Fluorescence Detection Method 429
Takashi Hiroi, Kazushi Yoshimura, Takanori Ninomiya, Toshimitsu Hamada, Yasuo Nakagawa, Shigeki Mio, Kouichi Karasaki and Hideaki Sasaki, Hitachi, Ltd. , Japan

SD Shape Analysis & Recognition

Modal Descriptions for Recognition and Tracking (Invited) 435
Alex P. Pentland, Massachusetts Institute of Technology, USA
Statistical Reliability of 3-D Computing from Images 445
Kenichi Kanatani, Gunma University, Japan
An Accurate 3d Vision System Using a Projected Grid for Surface Geometrical Study 449
Latifa Guisser, René Payiissat and Serge Castan, Universite Paul Sabatier, France
Three Dimensional Boundary Detection Using Higher-Order Surface Fitting and Directional Smoothing 453
Tomas Gustavsson and Quan Liang, Chalmers University of Technology, Sweden
Development of a System for Producing Stereo Ground Models by Optical Lithography 457
Yoshinao Aoki*, Shin Tanahashi*, Osamu Kinoshita* and Hideaki Nakamura**, *Hokkaido University, **Hokkaido Chizu Co. Ltd,. Japan

Human Motion & Face Analysis

Extracting Feature Points on Human Eye Photographs 461
Shizuo Sakamoto*, Yoko Miyao** and Johji Tajima*, *NEC, **NEC Software Limited, Japan
Target Image Extraction for Face Recognition Using the Sub-Space Classification Method 465
Shigeru Akamatsu*, Tsutomu Sasaki**, Hideo Fukamacni*** and Yasuhito Suenaga**, *ATR, **NTT, ***NTT Software Corp. , Japan
Human Face Analysis Based on Distributed 2d Appearance Models 469
Yasushi Sumi and Yuichi Ohta, University of Tsukuba, Japan
Real-Time Detection of Pointing Actions for a Glove-Free Interface 473
Masaaki Fukumoto, Kenji Mase and Yasuhito Suenaga, NTT, Japan
Qualitative Visual Interpretation of 3d Hand Gestures Using Motion Parallax 477
Roberto Cipoila, Yasukazu Okamoto and Yoshinori Kuno, Toshiba Corp. , Japan

Poster Session 3

A 'Hyper-Pyramid' Architecture for Massively Parallel Image Processing 483
Mohamed Akil and Eric Dujardin, Laboratoire I. A. A. L, France
Applications of the Color Conversion System Using the LUT and Interpolation to the Real-Time Color Recognition 487
Hideto Motomura, Katsuhiro Kanamori, Teruo Fumoto and Hiroaki Kotera, Matsushita Research Institute Tokyo, Inc. , Japan
An Efficient Parallel Implementation of the Laplacian Pyramid Algorithm 491
Min Xue*, Abdelhamid Hachicha* and Alain Merigot*, *ESIGETEL, **Université Paris-Sud, France
A Rule-Based Expert System for Low Level Image Processing 495
Balaram Bhattacharyya, Visva-Bharati University, India
On a Basic Consideration of the Warp Model of Hough Transform 499
Hiioyasu Koshimizu* and Munetoshi Numada**, *Chukyo University, **Lossev Technology Co. Ltd. , Japan
A Stroke Index for Document Image Analysis Based on the MCR Expression Method 503
AbdelMalek B. C. Zidouri, Supoj Chinveeraphan and Makoto Sato, Tokyo Institute of Technology, Japan
A Document Analysis Method Based on a Consistent Structural Model of Document Elements and Pages 507
Masaharu Ozaki* and Yuusuke Ishida**, *Fuji Xerox Palo Alto Lab. , USA, **Fuji Xerox Co. ,Ltd. , Japan
Improvement of Text Image Recognition Based on Linguistic Constraints 511
Koichi Kise, Tadamichi Shiraishi, Shinobu Takamatsu and Hiroji Kusaka, University of Osaka Prefecture, Japan
Extraction and Reconstruction of Road Segments by Spatial Filters 515
Wookhyun Kim*, Takashi Furukawa**, Yuzo Hirai and Ryuji Tokunaga*, *University of Tsukuba, **Nippon Steel Corporation, Japan
Postprocessing for Character Recognition Using Keyword Information 519
Hisao Niwa, Kazuhiro Kayashima and Yasuharu Shimeki, Matsushita Elec. Ind. Co. , Ltd. , Japan
Interpretation of Optical Flow through Neural Network Learning 523
Minami Miyauchi*, Masatoshi Seki*, Akira Watanabe** and Arata Miyauchi**, *SANNO College, **Musashi Institute of Technology, Japan
A High-Speed Image Processor for Detection of Pavement Cracks 529
Satoshi Abe**,*, Taizo Okano**, Hisao Sato*, Koki Sengoku**, Nobuaki Shimada* and Noboru Kazuki*,*University of Tokyo, **Array Corporation, Japan
Combining Motion Smoothness and Grayscale Consistency in Analysing Real World Human Body Motion 533
Mo Weiguo, Fudan University, PRO
A New Multi-Stage Face Identification in Motion Picture 537
Akihiko Sugikawa, Toshiba Corp. , Japan
Detection of Scene Changes for Efficient Image Transmission from a Moving Camera 541
Joan Batlle Grabulosa* and Antonio B. Martinez**, *Universitat de Girona, **Universidad Politecnica de Catalunya, Spain
Interactive Surface Display for 3d Medical Images Using Multilayer Range Images 545
Hideyuki Ban, Akihide Hashizume and Ryuuichi Suzuki, Hitachi, Ltd. , Japan
Biological Object Classification and Identification on Light Microscopy Images 549
Mylène Roussel*'**, X. W. Tu* and D. Fontaine*, *Université de Technohgie de Compiègne, **Laboratoire d'lnformatique Avancée de Compiègne, France
Agricultural Products Sorting System by Using High-Speed Image Pipelined Processor and FA Components 553
Kazuhiko Fukuda*, Makoto Watanabe*, Masao Nitoh*, Yuh Maruko* and Youji Suzuki**, *FUJT FACOM Corporation, **FUJI Electric Co. , Ltd,, Japan
Parallel Analysis of Non Convex Shapes Digitized on the Hexagonal Grid 557
Gunilla Borgefors* and Gabriella Sanniti di Baja**, *Swedish Defence Research Establishment, Sweden, **Istituto di Cibernetica, Italy
2-D Form Descriptors Based on a Normalized Parametric Polar Transform (UNL Transform) 561
T. W. Rauber and A. S. Steiger-Garçäo, Universidade Nova de Lisboa, Portugal
A Real-Time Deformable Clay Model for Rotationally Symmetric Objects 567
Katsuyuki Kamei, Yasuaki Nakamura and Shigeru Abe, Mitsubishi Electric Corporation, Japan
A CAD Based Knowledge Vision System for 3d Objects Recognition 571
R. K. Kunchev and M. G. Milanova, Technical University, Bulgaria
3-D Curved Object Recognition Based on Parameter Nets Weighted with Feature Saliency. . . . 575
Hongbin Zha and Tadashi Nagata, Kyushu University, Japan
Transform Clustering for Model-Image Feature Correspondence 579
Raj Talluri and J. K. Aggarwal, University of Texas at Austin, USA
Illumination-Invariant Active Vision 533
Morito Shiohara and Hiroshi Kamada, FUJITSU Laboratories Ltd. , Japan
3-D Shape Measurement by Extraction of Characteristics Using Image Processing 587
Yoshiharu Morimoto and Yutaka Yoshioka, Osaka University, Japan
Shape from Shading on Textured Cylindrical Surface - Restoring Distorted Scanner Images of Unfolded Book Surfaces 591
Toshikazu Wada and Takashi Matsuyama, Okayama University, Japan
Surface Reconstruction with Triangular Patches from Multiscale Range Images 595
Yoshifumi Kitamura, Takeo Kimura, Masatoshi Okutomi and Hideyuki Tamura, Canon Inc. , Japan
A Technique for Reconstructing Shape of Specular Surfaces 599
Tetsuo Miyake*, Ken Uemura**, Shigeyuki Seto**, Yasunari Saito** and Kazuaki Shimizu**, *Toyohashi University of Technology, **Asahi Glass Co. Ltd. , Japan
Recovering Depth in Stereo Calculation 603
Jesse S. Jin, Wai-kiang Yeap and Brian G. Cox, University of Otago, New Zealand
Primitive Based Stereo for the Can-Picking Robots 607
Hironobu Takahashi*, Hideo Hirono*, Hajime Terasaki* and Fumiaki Tomita**, *Sanyo Electric Company, **Electrotechnical Laboratory, Japan
Implementation of an Object-Oriented & Declarative Language for Image Understanding 611
E-ren Chuang* and David Sher*, *Kaohsiung Polytechnic Institute, ROC, **State University of New York at Buffalo, USA
A Monocular Technique for the Reconstruction of 3d Shape Using a Cooperating Robot Arm 615
Charles Allen and Roy Booth, University of Newcastle upon Tyne, UK

Applications 2

New Machine Vision Applications in Germany (Invited) 619
Claus-E. Liedtke, Universität Hannover, Germany
In-Motion Inspection of Obstacles around Railways by a Highly Accurate Laser-Sectioning Method 629
Y. Jin*, Y. Goto*, H. Naito*, Y. Aono* and A. Iwake**, *Kobe Steel Ltd. , **Central Japan Railway Co. , Japan
Automatic Digital Elevation Model Extraction Using SPOT Satellite Image 633
Jeong-Kee Kim, Chan-Eung Park and Kwae-Hi Lee, Sogang University, Korea
Probe Shape Recovery in Scanning Probe Microscopy 639
Gopal Sarma Pingali and Ramesh Jain, University of Michigan, USA
3d Reconstruction of Plants 643
M. Chapron*, N. Ivanov* **, P. Boissard** and P. Valery, *ENSEA-ETIS, **INRA Bioclimatologie, France

** Late Arrival **

A Neural Network Based Method for Automated Classification of Sheep Leather Images 647
Jianqin Liu, Nanning Zheng, Li Wei and Qingyuan Wang, Xian Jiaotong University, PRC