Share Email Print

Proceedings Paper

Statistical Mechanics and Pattern Recognition: A New Feedback Technique
Author(s): Martin L. Brady; Raghu Raghavan; Joseph Slawny
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

In this paper we describe a new pattern recognition method which will allow for a synthesis of approaches based on prior analyses and contextual information with those based on Artificial Neural Networks. We develop a new iterative neural network framework based on a fully parallel probabilistic feedback dynamics. The method allows knowledge about the problem to be built into the network structure. In addition, heuristic search techniques can be incorporated by modifying the probabilities. We illustrate this method with a pattern recognition problem on an infrared image. The performance is better than that of competing methods.

Paper Details

Date Published: 5 September 1989
PDF: 11 pages
Proc. SPIE 1099, Advances in Image Compression and Automatic Target Recognition, (5 September 1989); doi: 10.1117/12.960457
Show Author Affiliations
Martin L. Brady, Lockheed R&DD (United States)
Raghu Raghavan, Lockheed R&DD (United States)
Joseph Slawny, Virginia Polytechnic Institute and State University (United States)

Published in SPIE Proceedings Vol. 1099:
Advances in Image Compression and Automatic Target Recognition
Andrew G. Tescher, Editor(s)

© SPIE. Terms of Use
Back to Top