Abstract
Purchase PDF (2923 K)
E-mail Article
Add to my Quick Links
Cited By in Scopus (0)
Purchase PDF (549 K)
doi:10.1016/0020-0255(88)90013-8 
Copyright © 1988 Published by Elsevier Science Inc.
A unified approach to artificial intelligence, pattern recognition, image processing and computer vision in fifth-generation computer systems
References and further reading may be available for this article. To view references and further reading you must purchase this article.
D. Dutta Majumder
Received 15 August 1987.
Abstract
One of the goals of research for the last two decades or so in pattern recognition and its subareas (such as image processing, analysis and understanding, speech processing, analysis and understanding, natural-language processing and understanding, computer vision techniques, etc.) has been to develop fundamental techniques for flexible interactive intelligent man-machine interfaces for computers. The author argues that the evolution to the fifth-generation computer systems (FGCS), as defined by Japanese scientists, will require, among other things, advances in pattern recognition and its subareas, not only to achieve man-machine interfaces with a natural mode of communication, but also to implement the basic mechanisms of inference, association and learning, which are inherent in pattern recognition and therefore essential to the core functions of FGCS. The next-generation computers will be knowledge-based systems, which constitute a subdomain of artificial-intelligence (AI) techniques and so AI provides the essential link between the abovementioned pattern-recognition domains and different application systems. After introducing a natural and intrinsic link between the evolving subjects of AI and computer-vision research, particularly in the context of the next generation of computer-system research, the paper presents an overview of the framework of current image-understanding research from the points of view of knowledge level, information level, and complexity. Because a general-purpose computer-vision system must be capable of recognizing 3-D objects, the paper attempts to define the 3-D object-recognition problem and discusses basic concepts associated with this problem. The major application areas often are industrial vision systems and scene analysis in aerial photography. No attempt is made to discuss other essential conceptual building blocks, such as software engineering, computer architecture, and VLSI technology, unless these become especially relevant to the topics of the paper. There is a section on limitations of perception, learning and knowledge for computing machines.
