ICSC'95 CONFERENCE PROGRAMME ICSC '95 - Third International Computer Science Conference: Image Analysis Applications and Computer Graphics Nikko Hotel, HONG KONG, 11-13 December 1995 Organised and Sponsored by the IEEE Hong Kong Section, Computer Chapter. In cooperation with IEEE Computer Society, International Association for Pattern Recognition (IAPR), ACM (HK). MESSAGE FROM THE GENERAL CHAIRMAN With the advance of imaging and image synthesis technologies, traditional text-based computing is giving way to computational modalities which manipulates, synthesise, and analyse visual data. We have only just begun to see the benefits of such computation modules in the forms of multimedia information kiosks, analysis and inspection systems for medical and industrial images, and realistically rendered imageries in TV commericals and motion pictures. The ability to receive, process and deliver data in visual form is paramount to the efficient perception and understanding of complex information. This cannot be more clearly demonstrated in the areas of medical diagnosis, engineering design, and system monitoring. The needs to improve the performance and cost-efficiency in these areas have led directly to the recent developments in data visualisation, medical imaging, industrial inspection systems, Computer-aided design and manufacturing (CAD/CAM) systems, Geographic Information Systems (GIS), and Automated Mapping and Facility Management (AM/FM) systems. In ICSC'95, the Third International Conference on Computer Science to be held in Hong Kong by the IEEE (HK) Section Computer Chapter, we will present the latest developments of the associate enabling technologies that make such systems possible. Particularly, the programme of image analysis applications and computer graphics aim to highlight synergies in the two areas. The convergence of computer graphics and image analysis techniques cannot be better illustrated in one of our plenary sessions focussing on Model-based Video Coding by Prof. T. Huang. The impact on the movie industry due to the latest developments in computer graphics and animation is clearly demonstrated in our other plenary session by Mr. J. Lasseter from Pixar. Prof. Ahuja's invited talk on a novel approach to visual imaging shows us the latest breakthrough in imaging technology while Prof. Kasturi's tutorial gives us a comprehensive review of the state-of-the-art and current limitations in document image analysis. I hope you will find ICSC'95 an occasion to meet friends and colleagues who have helped shaping the technical developments in the fields of image analysis and computer graphics and, at the same time, find time to explore and to enjoy the dynamic environment that makes Hong Kong unique among the major financial cities of the World. Horace H S Ip Conference Chairman, ICSC'95 ORGANISING COMMITTEE General Chair: Horace H S Ip (City University of Hong Kong) Program Chair: Roland Chin (Hong Kong University of Science and Technology) Image Analysis Applications Co-chair: T.C. Pong (Hong Kong University of Science and Technology) Computer Graphics Co-chair Avi C. Naiman (Hong Kong University of Science and Technology) Treasurer: H F Ting (University of Hong Kong) Registration: Joseph Ng (Hong Kong Baptist University) Andrew Luk (City University of Hong Kong) Publicity: Ronald Chung (Chinese University of HK) H T Tsui (Chinese University of Hong Kong) Tong Lee (Chinese University of Hong Kong) Publications: John C M Lee (Hong Kong University of Science and Technology) Local Arragements: Karl Leung (Hong Kong Polytechnic University) IEEE (HK) representatives: Richard Chen, L W Chan ACM (HK) representative: Vincent Wong PROGRAM COMMITTEE Image Analysis Applications Jake Aggarwal (University of Texas) Narendra Ahuja (University of Illinois) Terry Caelli (Curtin University of Technology) Francis Chin (The University of Hong Kong) Charles Dyer (University. of Wisconsin) Robert Haralick (University of Washington) Thomas Huang (University of Illinois) Anil Jain (Michigan State University) Josef Kittler (University of Surrey) Song De Ma (Institute of Automation, Beijing) Linda Shapiro (University of Washington) Yoshiaki Shirai (Osaka University) Ching Y. Suen (Concordia University) Demetri Terzopoulos (University of Toronto) Saburo Tsuji (Osaka University) Andrew Wong (University of Waterloo) Guang-You Xu (Tsinghua University) Additional Reviewers Oscar Au Hong Kong University of Science and Technology W.K. Cham Chinese University of Hong Kong Chorkin Chan The University of Hong Kong Francis Chan The University of Hong Kong William Cheung Hong Kong University of Science and Technology Andrew Choi The University of Hong Kong Ronald Chung Chinese University of Hong Kong Andrew Horner Hong Kong University of Science and Technology Peter Tsang City University of Hong Kong Horace H S Ip City University of Hong Kong C.M. Lee Hong Kong University of Science and Technology Tong Lee Chinese University of Hong Kong Qing Li Hong Kong University of Science and Technology Zhaoping Li Hong Kong University of Science and Technology Andrew Luk City University of Hong Kong Isaac Ng Hong Kong University of Science and Technology W.Y. Ng Chinese University of Hong Kong Helen Shen Hong Kong University of Science and Technology S.K. Tso City University of Hong Kong H.T. Tsui Chinese University of Hong Kong Lei Xu Chinese University of Hong Kong Herb Yang University of Saskatchewan D.Y. Yeung Hong Kong University of Science and Technology Raymond Yip City University of Hong Kong Kelvin Yuen City University of Hong Kong P.C. Yuen Hong Kong Baptist University Computer Graphics John Amanatides (York University) George Baciu (Hong Kong University of Science & Technology) Tony DeRose (University of Washington) Eugene Fiume (University of Toronto) Alain Fournier (University of British Columbia) Martin Goebel (Fraunhofer Institute for Computer Graphics) Pat Hanrahan (Stanford University) Siu-chi Hsu (The Chinese University of Hong Kong) Kin-chuen Hui (The Chinese University of Hong Kong) Tosiyasu Kunii (The University of Aizu) Rynson Lau (Hong Kong Polytechnic University) Andrew Layfield (City University of Hong Kong) Eihachiro Nakamae (Hiroshima Prefectural University) Qunsheng Peng (Zhejiang University) Demetri Terzopoulos (University of Toronto) Wenping Wang (The University of Hong Kong) Keith Waters (Digital Equipment Corporation) Geoff Wyvill (Univeristy of Otago) Michael Zyda (Naval Postgraduate School) Additional Reviewers Thomas Fruehauf Takafumi Hayashi Jens Herder Runhe Huang Horace H S Ip Kenjiro Miura Karol Myszkowski Oleg Okunev Alexander Pasko V. Savchenko Peter Tsang Co-sponsoring organisations: City University of Hong Kong, Hong Kong Baptist University, Hong Kong Computer Society, Hong Kong Institution of Engineers, Hong Kong Polytechnic University, Hong Kong Society for Multimedia and Image Computing, The Chinese University of Hong Kong, The University of Hong Kong. Sponsored by The Croucher Foundation, Silicon Graphics Ltd., SUN Microsystems of California Ltd., Hong Kong Television Broadcasts Ltd. and Motorola Semiconductors Hong Kong Ltd. INVITED TALKS DAY 1, Monday, 11 December 1995: Prof. Thomas. S. Huang Beckman Institute for Advance Science and Technology University of Illinois at Urbana-Champaign U.S.A. Title: 3D MODEL-BASED VIDEO CODING: Computer Vision Meets Computer Graphics ABSTRACT Although the two disciplines of Computer Vision and Computer Graphics originated and have evolved more or less independently of each other, in many important recent applications they have met and become intertwined. We shall describe one such application: Trying to achieve very low bitrate video transmission by a 3D model-based approach in the context of video phone and teleconferencing. The idea is that if a 3D model of a person is available at the receiving end, then only movement information needs to be extracted and transmitted, which hopefully requires a very low bitrate. Our talk will concentrate on the modeling, analysis, and synthesis of facial movement and hand gestures. Encouraging preliminary results will be presented. However, it will be seen that many challenging issues have to be resolved before the model-based approach can be viable. DAY 2, Tuesday, 12 December 1995: John Lasseter Director & Animator Vice President, Creative Development, Pixar, U.S.A. Title: CREATING MEMORABLE CHARACTERS WITH COMPUTERS ABSTRACT With the latest computer animation software tools, making objects move is becoming easier and easier. But making those easy. Computer animation software tools will never do that for you. To make characters come alive takes a knowledge of traditional animation principles and acting, regardless of the animation medium. Remember, computers don't animate ... people do. DAY 3, Wednesday, 13 December 1995: Prof. Narendra Ahuja Beckman Institute, Coordinated Science Laboratory, and Department of Electrical and Computer Engineering University of Illinois at Urbana-Champaign TITLE: A NONFRONTAL IMAGING CAMERA ABSTRACT This talk will describe a new approach to visual imaging called nonfrontal imaging. This has lead to the design of a new type of camera which has three salient characteristics: (1) It can provide panoramic images of upto 360 degree views of a scene. (2) Each object is in complete focus regardless of its location. (3) The camera also delivers the coordinates of each focusable, visible scene point, in addition to and registered with a sharp image. The Nonfrontal Imaging Camera eliminates the need for mechanical adjustments required for focusing in the conventional technology. Panning, which is necessary to view different parts of the scene anyway, suffices as the sole mechanical action. This performance is achieved by exploiting a novel combination of optics and imaging geometry. The properties of the camera can be exploited in various ways to achieve novel functionalities. For example, the range estimates can be combined with the focused images to obtain stereo-viewable, focused, panoramic, 3D views of a scene using only one camera as the sensor. The talk will also review other results from our recent research in analysis, processing, synthesis and communication of video sequences. TUTORIAL Title: Document Image Analysis Techniques: An Overview Prof. Rangachar Kasturi, Professor of computer science and engineering, Pennsylvania State University, U.S.A. Objectives: This course will enable the participant to: 1. learn the basic principles of document image analysis methods for optical character and graphics recognition 2. become familiar with the capabilities and limitations of automatic document image processing techniques 3. understand the relationships among various system components to facilitate systematic evaluation of document image analysis systems 4. know the state-of-the-art in vectorizers for converting engineering drawings and maps. Contents: Document image analysis systems automatically extract formation from scanned images of paper-based documents. Such systems recognize characters, symbols, and lines, establish spatial and semantic relationships, and determine the overall structure. Their output facilitates efficient storage, retrieval, and editing of the documents' contents. The general procedure and sequence of methods used in document image analysis are: data captured preprocessing, segmentation and layout analysis, feature extraction and matching, text and graphics recognition and interpretation. An overview of each of these topics will be presented in this course. Applications of the techniques discussed include automatic processing of business letters and forms, conversion of engineering drawings and maps, input technical of mail pieces, and recognition of musical notes, shorthand scripts, etc. However, specific commercial systems will not be discussed. Intended Audience: Anyone who must deal with large volumes of paper-based documents and their conversion into computer readable form for efficient storage, retrieval, and manipulation. The course would help both computer engineers who design document analysis systems and managers who specify and evaluate such systems. Some familiarity with basic principles of digital image processing is helpful. About the Instructor: Rangachar Kasturi is a professor of computer science and engineering at the Pennsylvania State University. He received his Ph.D. degree in electrical engineering from Texas Tech University in 1982. Dr. Kasturi has directed many research projects in the document image analysis area. He is a coauthor of the text, Machine Vision, McGraw-Hill, 1995, and co-editor of the books, Document Image Analysis, Computer Vision: Principles and Applications, and Image Analysis Applications. He is the editor-in-chief of the IEEE Transactions on Pattern Analysis and Machine Intelligence. Text: L. O'Gorman and R. Kasturi, Document Image Analysis Techniques, IEEE Computer Society Press, 1994 (included in the tutorial fee) Duration: Half day. CONFERENCE PROGRAMME Day 1 8:45- 9:00 Opening Remarks 9:00-10:00 Invited Talk: T.S. Huang 10:00-10:20 Break 10:20-12:00 IA1a: Robot Navigation & Tracking CG1a: Scientific Visualization 12:00- 1:30 Lunch 1:30- 3:10 IA1b: Feature Matching & Detection CG1b: Geometric Modeling 3:10- 3:30 Break CG1c: Rendering 5:30 - 7:30 Cocktail Reception Day 2 9:00-10:40 IA2a: 3-D Image Analysis CG2a: Image Synthesis 10:40-11:00 Break 11:00-12:00 Invited Talk: John Lasseter 12:00- 1:30 Lunch 1:30- 3:10 IA2b: Biomedical Imaging CG2b: Simulation & Animation 3:10- 3:30 Break 3:30- 5:15 IA Poster Session 6:30 - 10:00 Conference Banquet Day 3 9:00-10:00 Invited talk: N. Ahuja CG3a: Curves & Surfaces 10:00-10:20 Break 10:20-12:00 IA3b: Application Systems CG3b: Human Models 12:00- 1:30 Lunch 1:30- 5:00 Tutorial Day 1 Invited Talk 3D Model-based Video Coding: Computer Vision Meets Computer Graphics T.S. Huang, University of Illinois at Urbana-Champaign, USA Session IA1a -- Robot Navigation & Tracking Autonomous Mobile Robot Navigation Using Fish-Eye Lenses Shishir Shah and J.K. Aggarwal, The University of Texas at Austin, USA High-Performance Tracking System Jiantao Huang and Jian-zhao Wang, Yale University, USA A 3D Predictive Visual Tracker for Tracking Multiple Moving Objects with a Stereo Vision System Yi-Ping Hung, Cheng-Yuan Tang, Zen Chen, Sheng-Wen Shih and Wei- Song Lin, Academia Sinica, National Chiao Tung University and National Taiwan University, ROC Vision Guided Circumnavigating Autonomous Robots Nick Barnes and Zhi-Qiang Liu, The University of Melbourne, Australia Force-driven Optimization for Correspondence establishment W.H. Wong and Horace H.S. Ip, City University of Hong Kong, Hong Kong Session CG1a -- Scientific Visualization The Deformed Cube: A Visualization Technique for 3D Velocity Vector Field Xundong Liang, Bin Li and Shenquan Liu, Institute of Computing Technology Academia Sinica, PRC Interactive Particle Tracing Algorithm for Unstructured Grids Jicheng Ren, Guangzhou Zeng and Shenquan Liu Institute of Computing Technology Academia Sinica, PRC Fast Resampling Using Vector Quantization Patrick C. Teo and Chase D. Garfinkle, Stanford University, USA A B-spline Surface Interpolation Technique for Reconstructing 3D Objects from Serial Arbitrary Shaped Planar Contours Meihe Xu, Zesheng Tang and Junhui Deng, Tsinghua University, PRC Session IA1b -- Feature Matching & Detection Two Methods for a Reliable Corner Detection in 2D Images Richard Lengagne, Olivier Monga, Cong Ge and Ma Song De INRIA, Domaine de Voluceau-Rocquencourt, France, and Chinese Academy of Sciences, PRC On the Deletability of Points in 3D Thinning R.Watzel, K.Braun, A.Hess, H.Scheich and W.Zuschratte Fachgebiet Digitaltechnik and Federal Intitute for Neurobiology Real-time Textured Object Recognition on Distributed Systems J. You, W.P. Zhu, H.A. Cohen and E. Pissaloux University of South Australia, La Trobe University and Universite Paris XI, France Off-Line Signature Verification without Requiring Random Forgeries for Training Nabeel A. Murshed, Flavio Bortolozzi and Robert Sabourin Centro Federal de Educacao Tecnologica do Paran (CEFET-PR) and Ecole de Technologie Superieure, France Noisy Subsequence Recognition Using Constrained String Editing Involving Substitutions,Insertions, Deletions and Generalized Transpositions B.J. Oommen and R.K.S. Loke, Carleton University, USA Session CG1b -- Geometric Modeling GEOFF - A Geometrical Editor for Fold Formation Hing N. Ng and Richard L. Grimsdale, University of Sussex, UK Simplification of Polygonal Surface with Attributes Eihachiro Nakamae, Jianyun Chai, Hiroyuki Inuyama, and Fujiwa Kato Hiroshima Prefectural University, Sanei Co., Ltd. and Tokyo Electric Power Co., Inc., Japan, and Tsinghua University, PRC Reducing Polygonal Data by Structural Grouping Algorithm Daisuke Nishioka and Mikio Nagasawa, Ultra-High Speed Ntework and Computer Technology Laboratories, Japan An Object-Oriented Architecture for Chinese Character Composition Ivan S.B. Wong and Avi C. Naiman, Hong Kong University of Science and Technology, Hong Kong Session IA1c -- Document Processing & Character Recognition Bank Check Reading: Recognizing the Courtesy Amount Valeri Anisimov, Nikolai Gorski, David Price, Olivier Baret and Stefan Knerr, SPIIRAS, 39, 14th Line and A2iA, Tour CIT, BP59 An Automatic Extraction Approach of Road Information on the Basis of Recognition of Character Regions Masakazu Nishijima and Toyohide Watanabe, Nagoya University, Japan Interpreting Music Manuscripts: A Logic-Based, Object-Oriented Approach W. Brent Seales and Arcot Rajasekar, University of Kentucky, USA On-line Chinese Character Recognition with Attributed Relational Graph Matching Jianzhuang Liu, W. K. Cham and Michael M.Y. Chang, The Chinese University of Hong Kong, Hong Kong On-line Handwritten Alphanumeric Character Recognition Using Feature Sequences Xiaolin Li and Dit-Yan Yeung, The Hong Kong University of Science and Technology, Hong Kong Session CG1c -- Rendering An Adaptive Supersampling Method Rynson W.H. Lau, Hong Kong Polytechnic University, Hong Kong Dynamic Memory Mapping for Window Based Display System C.M. Ng, University of Ulster, UK Convert Non-convex Meshes to Convex Meshes for Depth Sorting in Volume Rendering Yong Zhou and Zesheng Tang, Tsinghua University, PRC A New Chain Coding Scheme for Cursive Script and Line Drawings H. Yuen and L. Hanzo, University of Southampton, UK Session IA2a -- 3-D Image Analysis Adaptive Hierarchical Indexing and Constrained Localization: Matching Characteristic Views Gunter Bellaire and Matthias Lebbe, Institut fur Technische Informatik, TU Berlin Statistical Estimation for Exterior Orientation from Line-to-Line Corres pondences Chung-Nan Lee and Robert M. Haralick, National Sun Yat-Sen University, ROC, and University of Washington, USA High Level Scene Interpretation using Fuzzy Belief Sandy Dance and Zhi-Qiang Liu, University of Melbourne, Australia Estimating Shape and Reflectance of Surfaces by Color Image Analysis Yingli Tian and Hungtat Tsui, The Chinese University of Hong Kong, Hong Kong Feature Detection Using Oriented Local Energy for 3D Confocal Microscope Images Chris Pudney, Peter Kovesi and Ben Robbins, The University of Western Australia, Australia Session CG2a -- Image Synthesis Advancing Front Meshing for Radiosity Solutions George Baciu and Rico K.W. Tsang The Hong Kong University of Science and Technology, Hong Kong An Efficient Cluster-based Hierarchical Progressive Radiosity Algorithm Karol Myszkowski and Tosiyasu L. Kunii, The University of Aizu, Japan A Model of Skylight and Calculation of Its Illuminance Eihachiro Nakamae, Guofang Jiao, Katsumi Tadamura and Fujiw Kato, Sanei Giken Co. Ltd., Hiroshima Prefectural University and Tokyo Electrical Power Company, Japan Ray Tracing Stereoscopic Images Gabriel K.P. Fung, Horace H.S. Ip and Ken C.K. Law, City University of Hong Kong, Hong Kong Day 2 Invited Talk Creating Memorable Characters with Computers John Lasseter, Pixar, USA Session IA2b -- Biomedical Imaging Computer Assisted Lung Cancer Diagnosis Based on Helical Images K.Kanazawa, M.Kubo, N.Niki, H.Satoh, H.Ohmatsu, K.Eguchi and N.Moriyama, University of Tokushima, Japan Computer-Aided Lung Nodule Detection in Chest Radiography Maria J. Carreira, Diego Cabello, Manuel G. Penedo and Jose M. Pardo, Univeristy of Santiago de Compostela and University A Corusa Neural Networks for the Segmentation of Magnetic Resonance Images Rachid Sammouda, Noboru Niki and Hiromu Nishitani, University of Tokushima, Japan Multiresolution Adaptive K-means Algorithm for Segmentation of Brain MRI B. C. Vemuri, S. Rahman and J. Li, University of Florida, USA Computer-Assisted Analysis and 3D Visualization of Blood Vessels Based on Cone-Beam CT Images Yoshiki Kawata, Noboru Niki and Tatsuo Kumazaki, University of Tokushima, Japan Session CG2b -- Simulation & Animation An Interface for Synthesizing 3D Multibody Structures George Baciu and Brian L.P. Lee The Hong Kong University of Science and Technology, Hong Kong Importance Ordering for Real-Time Depth of Field Paul Fearing, University of British Columbia, Canada A Behavioural Control Framework for Computer Animation using AI Techniques Carlos S.N. Ho and Richard L. Grimsdale, University of Sussex, UK Time-Space Weighting for Image Sequence Quantization Hagit Zabrodsky Hel-Or, Stanford University, USA Day 3 Invited Talk A Nonfrontal Imaging Camera N. Ahuja, University of Illinois at Urbana-Champaign, USA Session CG3a -- Curves & Surfaces Modifying and Controlling of Smooth Closed Surfaces Lizhuang Ma and Qunsheng Peng, Zhejiang University, PRC Designing of 3D Rectangular Objects Muhammad Sarfraz, King Fahd University, Saudi Arabia Session IA3b -- Application Systems Classification Algorithm for Multi-Echo Magnetic Resonance Image Using Gibbs Distributions Junchul Chun and Ian R. Greenshields, Kyonggi University and University of Connecticut, USA Parameter Estimation for SAR Image by a Model Based Approach Fang Luo, Liu Lu and Z. Houkes, International Institute for Aerospace Survey and Earth Science and University of Twente A Synthesized Computer Recognition System for Human Hands Chuanxue Wang, Hanqing Lu and SongDe Ma, Institute of Automation, Chinese Academy of Sciences, PRC Independent Hand Gesture Recognition in HandTalker Wen Gao and Shuanglin Wang, Harbin Institute Technology, PRC, and Artificial Intelligent Laboratory, MIT, USA An Adaptive Estimation and Segmentation Technique for Determination of Major Maceral Groups in Coal J. Dehmeshki, M.F. Daemi, B.P. Atkin and N.J. Miles, University of Nottingham, UK Session CG3b -- Human Models Expression and Motion Control of Hair using Fast Collision Detection Methods Makoto Ando and Shigeo Morishima, Seikei University, Japan, and University of Toronto, Canada 3-D Emotion Space for Interactive Communication Fumio Kawakami, Motohiro Ohkura, Hiroshi Yamada, Hiroshi Harashima and Shigeo Morishima, Seikei University, Kawamura College, Japan, and University of Toronto, Canada Iterative Human Facial Expression Modeling Antai Peng and Monson H. Hayes, Georgia Technical University, USA Poster Session Shape from Shading Using Near Point Light Sources Sheng-Liang Kao and Chiou-Shann Fuh, National Taiwan University, ROC Feature Replenishment for Long-Term Visual Motion Tracking Tak-Keung Cheng, Les Kitchen and Zhi-Qiang Liu, The University of Melbourne, Australia An Imprecise Real-Time Image Video Transmission Algorithm Albert Mo Kim Cheng and Xiaofen Huang, University of Houston, USA Mechanisms for Automatic Extraction of Primary Features for Video Indexing Donald Adjeroh and Moon Chuen Lee, The Chinese University of Hong Kong, Hong Kong An Estimation of Low Bound for Two-Dimensional Image Compression Coding Huijuan Li, Qingdong Yao, Jae-Ho Choi and Hoon-Sung Kwak, Chonbuk National University and Zhejiang University, PRC Texture Comparison Based on Selected Texture Primitives David K.Y. Chiu and David A. Gadishev, University of Guelph, Canada Texture Analysis of Ultrasonic Images Using Backpropagation Neural Networks Jo Ann Parikh, John DaPonte and Meledath Damodaran, University of Houston, Southern Connecticut State University and University of Bridgeport, USA B-spline Based Multiscale Signal Derivative Filtering Ge Cong and SongDe Ma, Institute of Automation, Chinese Academy of Sciences, PRC Contour Decomposition Using Dominant points and Moment Difference Method P.C. Yuen, S.D. Ma, J. Liu and Y.S. Yeung, Hong Kong Baptist University and Chinese Academy of Sciences, PRC An Inherent Probabilistic Aspect of the Hough Transform Zhanyi Hu and Songde Ma, Institute of Automation, Chinese Academy of Sciences, PRC A Fuzzy Structural Approach to Handwritten Word Recognition Richard Buse and Zhi-Qiang Liu, The University of Melbourne, Australia An Arabic OCR Using Neural Network Classifiers Hazem Raafat and Gasser Auda, Kuwait University and University of Waterloo, Canada Arabic Characters Recognition Based on MCR A. Zidouri, S. Chinveeraphan and M. Sato, Tokyo Institute of Technology, Japan Geographic Map understanding. Algorithms for Hydrographic Network Reconstruction R. Mariani, M.P. Deseilligny, J. Labiche, Y. Lecourtier and R. Mullot IGN/DT/SR, Laboratoire MATIS, LACP, Universite de Caen and Lai-Lacis. Automatic Analyzing of a Weaving Design With the Spatial Frequency Components Ken'ichi Ohta, Yoshito Nonaka and Fujio Miyawaki, Himeji Insititute of Technology, Japan Visual Inspection of Watermeters used for Automatic Calibration Robert Sablatnig, Technical University Vienna, Austria Computer Aided Diagnosis in Radiology S. Vitulano, C.Di Ruberto, M.Nappi, Universite di Cagliari-Via S.Giorgio E. Wenger, V.N. Karnaukhov, A. Haidinger and N.S. Merzlyakov, Austrian Academy of Sciences, Austria, and Russian Academy of Sciences, Russia Document Layout Analysis Using Pattern Classification Method Masaki Yamaoka and Osamu Iwaki, NTT Data Communications Systems Corporation, Japan Recognition of Engineering Drawings Based on Frame Structure Theory Xu Yaodong and Ying Daoning, Zhejiang University, PRC FERSA: Lip-Synchronous Animation Patricia A. Griffin and Han Noot, GB Amsterdam, The Netherlands INQUIRIES Please send all inquiries about ICSC'95 to ICSC'95, Department of Computer Science, Hong Kong University of Science and Technology, Clear Water Bay, Hong Kong. E-mail: icsc@cs.ust.hk, FAX: (+852) 2358-1477.