Springer, 1983. — 413 p.This book consists of papers presented at an international symposium sponsored and organised by The Rank Prize Funds and held at The Royal Society, London, on 27-29 September, 1982. Since the inception of the Funds, the Trustees and their Scientific Advisory Committee on Opto-e1ectronics have considered that the scope of optoelectronics should extend to cover the question of how the eye transduces and processes optical information. The Funds have aimed to organise symposia on topics which, because of their interdisciplinary nature, were not well covered by other regular international scientific meetings. It was therefore very appropriate that the 1982 symposium should be on Physical and Biological Processing of Images. The purpose of the symposium was to bring together scientists working on the physiology and psychology of visual perception with those developing machine systems for image processing and understanding. The papers were planned in such a way as to emphasise questions of how image-analysing systems can be organised, as well as the principles underlying them, rather than the detailed biophysics and structure of sensory systems or the specific design of hardware devices. As far as possible, related topics in biological and artificial systems were considered side by side. The initial stages of image processing, whether physical or biological, consist of fairly simple, usually local, transformations of the array of intensity values in the image. However, to derive any useful information from the image, operations are needed which compute higher-level descriptions in terms of motion, stereo, and segmented regions, and ultimately in terms of the identity of objects and their layout in space. The topics of the papers were selected to span this whole range of image-processing problems. If we can understand how to mechanise image interpretation. a rich harvest of applications will follow. Applications in medical imaging, remote sensing, and character recognition are explicitly considered here. and the possibilities for robotics frequently arose in discussion. The continuing fall in the cost of information processing and storage components makes it feasible to construct practical systems which would have seemed extravagant fictions only a few years ago. Research into the field which some term the 'Physics of Computational Systems' is likely to be one of the key topics of the 1980's. Insights into how the brain organises and relates data could cata1yse the production of new and powerful computer architectures. Conversely, fundamental limitations which emerge from the study of computing and data organisation will help to confirm or reject models of human visual processes deduced by psychologists and physiologists. The proceedings of the symposium reflected the very great diversity of scientific interest in these problems; artificial intelligence, computer science, vertebrate and invertebrate neurophysiology, optical and electronic engineering, visual psychophysics, pattern recognition, and cognitive psychology were represented. The symposium made participants from each of these fields aware of the que~tions posed by other disciplines and the kinds of answers they can currently offer. It was clear that they had much in common. It was also clear that their different vocabularies, methods and backgrounds were a hurdle yet to be fully surmounted. This volume, we hope, will broaden the horizons of a wider audience of research workers and advanced students in all disciplines concerned with the processing and interpretation of images, and stimulate a continuing interaction between these diverse groups.Overviews Understanding Natural Vision Aspects of Visual Automation Constraints, Descriptions and Domain Mappings in Computational Vision Local Spatial Operations on the Image Matching Coding to Scenes to Enhance Efficiency Neighbourhood Operators Frequency Domain Visual Processing Psychophysical Evidence for Spatial Channels Detection and Recognition of Simple Spatial Forms Perceptual Filters Early Stages of Image Interpretation Visual Algorithms The Measurement of Visua1 Motion Visual Coding of Position and Motion Designing and Implementing an Algorithm to Extract Motion Information from Images Stereopsis Viewer-Centered Intensity Computations Pattern Recognition Statistical Image Processing Memory Networks for Practical Vision Systems Spatially Analogue Processes Matching Elastic Templates Analogue Representations of Spatial Objects and Transformations Higher Level Representations in Image Processing Contrast of Structured and Homogenous Representations Figure/Ground: Segmentation and Aggregation The Role of Attention in Object Perception Cooperative Grouping and Early Orientation Selection Recognition of Shape in Visible Surfaces Parallel Computers and Vision - Can Hardware Concepts Give Clues to "Brainware"? Image Processing in Perception and Cognition Postscript Image Interpretation: The Way Ahead?
Чтобы скачать этот файл зарегистрируйтесь и/или войдите на сайт используя форму сверху.