Advertisement

Computer Vision Systems for Industry: Comparisons

  • I. Aleksander
  • T. J. Stonham
  • B. A. Wilkie

Abstract

This article is written for those who are not familiar with the problems of automatic, computer-based pattern recognition. It surveys known methods in the light of opportunities offered by silicon chip technology.

The article also discusses some of the design decisions made in the creation of WISARD*, a fast pattern recognition computer built at Brunel University. Its structure has been optimized for silicon chip implementation.

Keywords

Pattern Recognition Discriminant Function Artificial Vision Pattern Class Silicon Chip 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Ullman, J. R. (1973) Pattern Recognition Techniques, Butterworth.Google Scholar
  2. 2.
    Batchelor, B. (1978) Pattern Recognition: Ideas in Practice.Google Scholar
  3. 3.
    Fu, K. S. (1976) Digital Pattern Recognition, Springer Verlag.CrossRefGoogle Scholar
  4. 4.
    Rutovitz, D. (1966) “Pattern Recognition” J. Roy Stat Soc., Series B/4, p. 504.Google Scholar
  5. 5.
    Aleksander, I. & Stonham, T. J. “A Guide to Pattern Recognition Using RAM’s”, IEE J. Dig. Sys & Computers,Vol. 2, No. 1 (1979(+)).Google Scholar
  6. 6.
    Gostick, R. W. ICL Tech fair, 1979, Vol. 1, No. 2, pp. 116–135.Google Scholar
  7. 7.
    Duff, K. J. B. Parallel Processing Techniques, in Batchelor (1978) (see above).Google Scholar
  8. 8.
    Aleksander, I. (1978) Pattern Recognition with Memory Networks, in Batchelor (1978) (see above).Google Scholar

Copyright information

© Crane Russak & Company Inc 1982

Authors and Affiliations

  • I. Aleksander
    • 1
  • T. J. Stonham
    • 1
  • B. A. Wilkie
    • 1
  1. 1.Department of Electrical Engineering & ElectronicsBrunel UniversityEngland

Personalised recommendations