Share Email Print

Optical Engineering

Optodigital neural network classifier
Author(s): Alain Bergeron; Henri H. Arsenault; Michel Doucet; Luc Veilleux; Denis J. Gingras
Format Member Price Non-Member Price
PDF $20.00 $25.00
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 two-layer neural network architecture for carrying out optodigital classification operations is proposed. The optical neural network implementation is suitable for pattern recognition and classification into digital format. The neural network is based on an optical correlator, an optoelectronic threshold, and an optodigital encoder. The module needs only one laser light source, and the light propagation from the input to the output is uninterrupted. The output is the class of the input pattern encoded in a digital format. Experimental results using different images and classes are presented. The classification can be changed arbitrarily by changing the encoding mask.

Paper Details

Date Published: 1 November 1997
PDF: 6 pages
Opt. Eng. 36(11) doi: 10.1117/1.601551
Published in: Optical Engineering Volume 36, Issue 11
Show Author Affiliations
Alain Bergeron, National Optics Institute (Canada)
Henri H. Arsenault, COPL/Univ. Laval (Canada)
Michel Doucet, National Optics Institute (Canada)
Luc Veilleux, National Optics Institute (Canada)
Denis J. Gingras, National Optics Institute (Canada)

© SPIE. Terms of Use
Back to Top