Abstract

Computer Vision Systems is a collection of papers presented at the Workshop on Computer Vision Systems held at the University of Massachusetts in Amherst, Massachusetts, on June 1-3, 1977. Contributors discuss the breadth of problems that must be taken into account in the development of general computer vision systems. Topics covered include the application of system engineering techniques to the design of artificial intelligence systems; representation and segmentation of natural scenes; and pragmatic aspects of machine vision. Psychophysical measures of representation and interpretation are also considered.
This monograph is divided into four sections: Issues and Research Strategies, Segmentation, Theory and Psychology, and Systems. The first chapter explores the problem of recovering the intrinsic characteristics of scenes from images, along with its implications for machine and human vision. The discussion then turns to special-purpose low-level vision systems that can be flexibly reconfigured as the need arises; design, development, and implementation of large systems from the human engineering point of view; and representation of visual information. The next section examines hierarchical relaxation for waveform parsing; the topology and semantics of intensity arrays; and visual images as spatial representations in active memory. The use of edge cues to recognize real-world objects is also analyzed.
This text will be a useful resource for systems designers, computer engineers, and scientists as well as psychologists.