Share Email Print
cover

Proceedings Paper

Photothermoplastic-based correlator using neural training algorithm for pattern recognition
Author(s): Boris S. Kiselyov; B. A. Novoselov; D. E. Okonov
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

A multichannel correlator based on photothermoplastic is presented in the paper. A one-layer neural network algorithm is realized for pattern recognition. Photothermoplastic holograms efficiency correction is investigated. Neural net learning process is realized using the filters efficiency adjustment. Recognition of the 5 images by 6 recorded feature patterns is shown.

Paper Details

Date Published: 7 December 1994
PDF: 9 pages
Proc. SPIE 2430, Optical Memory & Neural Networks '94: Optical Neural Networks, (7 December 1994); doi: 10.1117/12.195621
Show Author Affiliations
Boris S. Kiselyov, Institute of Optical Neural Technologies (Russia)
B. A. Novoselov, Institute of Optical Neural Technologies (Russia)
D. E. Okonov, Institute of Optical Neural Technologies (Russia)


Published in SPIE Proceedings Vol. 2430:
Optical Memory & Neural Networks '94: Optical Neural Networks
Andrei L. Mikaelian, Editor(s)

© SPIE. Terms of Use
Back to Top