This volume contains papers on Image Compression, Implementations, Feature Detection, 3-D Vision, Document Processing, Multi-Resolution Processing, Medical Imaging, Image Analysis Modelling, Neural Networks, Object Recognition, Remote Sensing, Dynamic Vision, Application, System & Architecture, Image Restoration/Enhancement and Image Segmentation.

This book constitutes the strictly refereed post-workshop proceedings of the Second International Workshop on Graphics Recognition, GREC'97, held in Nancy, France, in August 1997. The 34 thoroughly revised full papers presented were carefully selected for inclusion in the book on the basis of a second round of post-workshop reviewing. The book is divided into sections on vectorization and segmentation, symbol recognition, form processing, map processing, engineering drawings, applications and systems, performance evaluation, and a graphics recognition contest.

The papers in this volume deal with academic research topics as well as practical applications in AI. Special emphasis is given to computer vision, machine learning, neural networks mixed with theory of logic and reasoning, and practical applications of expert systems in industry and decision support.

This volume constitutes the proceedings of the 5th International Conference on Computer Analysis of Images and Patterns (CAIP'93), held in Budapest, Hungary, in September 1993. Formerly, the events in this biennial conference series were thought as a forum where East European researchers and professionals from academia and industry had an opportunity to discuss their results and ideas with Western colleagues active in image processing and pattern recognition. Now, CAIP'93 has a much more international scope, and in the future these conferences will not any longertake place only in East European countries, but roam throughout whole Europe. Besides invited talks by Belikova, Gimel'farb, Haralick and Roska, the volume contains 114 contributions, either presented as lectures or posters and carefully selected by a highly competent international program committee from a total of some 230 submissions; thus the book gives a thorough survey on recent research results and their applications in image processing and pattern recognition. The proceedings is organized in 20 sections, for example on image data structures, image processing, edges and contours, Hough transforms and related methods, shape, motion, 3-D vision, character recognition and document processing, biomedical applications, industrial applications, and neural networks.

Knowledge-based (or expert systems) and image processing have been applied to many domains but, although both fields frequently address common application areas, they are rarely applied together. Often a combined knowledge-based system and image processing approach can be highly appropriate and this book provides an insight into both areas and show students how a judicious mix of the two can result in a more effective system. The authors include detailed case studies to illustrate the two approaches as well as worked examples and solutions to problems throughout the text. Third and fourth year undergraduates and MSc students with some computer science background will find this book invaluable. Postgraduates and researchers looking for an introduction to either area - or ways to combine the two - will also welcome this clearly written and comprehensive text.

C. Amting Directorate General Information Society, European Commission, Brussels th Under the 4 Framework of European Research, the European Systems and Soft ware Initiative (ESSI) was part of the ESPRIT Programme. This initiative funded more than 470 projects in the area of software and system process improvements. The majority of these projects were process improvement experiments carrying out and taking up new development processes, methods and technology within the software development process of a company. In addition, nodes (centres of exper tise), European networks (organisations managing local activities), training and dissemination actions complemented the process improvement experiments. ESSI aimed at improving the software development capabilities of European enterprises. It focused on best practice and helped European companies to develop world class skills and associated technologies to build the increasingly complex and varied systems needed to compete in the marketplace. The dissemination activities were designed to build a forum, at European level, to exchange information and knowledge gained within process improvement ex periments. Their major objective was to spread the message and the results of experiments to a wider audience, through a variety ofdifferent channels. The European Experience Exchange (tUR~X) project has been one ofthese dis semination activities within the European Systems and Software Initiative.~UR~X has collected the results of practitioner reports from numerous workshops in Europe and presents, in this series of books, the results of Best Practice achieve ments in European Companies over the last few years.

With the advances in image guided surgery for cancer treatment, the role of image segmentation and registration has become very critical. The central engine of any image guided surgery product is its ability to quantify the organ or segment the organ whether it is a magnetic resonance imaging (MRI) and computed tomography (CT), X-ray, PET, SPECT, Ultrasound, and Molecular imaging modality. Sophisticated segmentation algorithms can help the physicians delineate better the anatomical structures present in the input images, enhance the accuracy of medical diagnosis and facilitate the best treatment planning system designs. The focus of this book in towards the state of the art techniques in the area of image segmentation and registration.

Going beyond the traditional field of robotics to include other mobile vehicles, this reference and "recipe book" describes important theoretical concepts, techniques, and applications that can be used to build truly mobile intelligent autonomous systems (MIAS). With the infusion of neural networks, fuzzy logic, and genetic algorithm paradigms for MIAS, it blends modeling, sensors, control, estimation, optimization, signal processing, and heuristic methods in MIAS and robotics, and includes examples and applications throughout. Offering a comprehensive view of important topics, it helps readers understand the subject from a system-theoretic and practical point of view.