Share Email Print

Proceedings Paper

Hybrid system using optical image compression and a neural system for parallel classification of images
Author(s): Philippe Gagne; Henri H. Arsenault
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

We introduce an optical classification method that allows the simultaneous comparison of an input object with multiple stored objects. The stored objects are compressed into one- dimensional vectors by means of an optical integrating ring detector that focuses the incident energy incident upon each ring to a point. The neural weights corresponding to the vectors are orthogonalized by means of a delta rule algorithm, and the classification site is carried out with the help of a joint transform correlator.

Paper Details

Date Published: 7 June 1996
PDF: 6 pages
Proc. SPIE 2751, Hybrid Image and Signal Processing V, (7 June 1996); doi: 10.1117/12.241997
Show Author Affiliations
Philippe Gagne, Univ. Laval (Canada)
Henri H. Arsenault, Univ. Laval (Canada)

Published in SPIE Proceedings Vol. 2751:
Hybrid Image and Signal Processing V
David P. Casasent; Andrew G. Tescher, Editor(s)

© SPIE. Terms of Use
Back to Top