Share Email Print
cover

Proceedings Paper

Pattern recognition system by a matched spatial filter and neural networks for imperfect input characters
Author(s): Shun-ichi Kamemaru; Tsutomu Baba
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

A hybrid pattern recognition system using a matched spatial filter and neural networks is described. In the system, a multiplexed matched spatial filter synthesized by feature-extracted reference patterns is used for optical processing and an algorithm of a neural network is used for digital processing. The concept of the neural is based on an associative memory. It enables the system to recognize unknown input patterns with slightly different shapes from the reference patterns, which we could not distinguish by a conventional matched spatial filter. Using the system, imperfect input letters such as given by poor printing are fairly recognized as well as the perfect ones are recognized.

Paper Details

Date Published: 9 November 1993
PDF: 9 pages
Proc. SPIE 2026, Photonics for Processors, Neural Networks, and Memories, (9 November 1993); doi: 10.1117/12.163572
Show Author Affiliations
Shun-ichi Kamemaru, Ibaraki Univ. (Japan)
Tsutomu Baba, Ibaraki Univ. (Japan)


Published in SPIE Proceedings Vol. 2026:
Photonics for Processors, Neural Networks, and Memories
Stephen T. Kowel; William J. Miceli; Joseph L. Horner; Bahram Javidi; Stephen T. Kowel; William J. Miceli, Editor(s)

© SPIE. Terms of Use
Back to Top