Share Email Print

Proceedings Paper

Optical hardware implementation of the two-layer neural network with the preprocessing unit for invariant pattern recognition
Author(s): Nickolay N. Evtikhiev; Boris N. Onyky; Dmitry V. Repin; Igor B. Scherbakov; Rostislav S. Starikov; Michael I. Zabulonov
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Optical pre-processing technique was combined with the two-layer neural network (TLNN), designed as multichannel acousto-optic modulator (MAOM) based optical vector-matrix multiplier (OVMM) by means of the PC interface. The system was applied to invariant recognition of planar objects. Pre-processing was presented by invariant moments based holographic feature extraction method. Optical hardware implementation (with the semiconductor laser and liquid crystal spatial light modulator) was investigated. Several other feature extraction methods (besides invariant moments) were applied and the possibility of the real-time implementation was considered.

Paper Details

Date Published: 15 March 1996
PDF: 9 pages
Proc. SPIE 2752, Optical Pattern Recognition VII, (15 March 1996); doi: 10.1117/12.235661
Show Author Affiliations
Nickolay N. Evtikhiev, Moscow State Engineering Physics Institute (Russia)
Boris N. Onyky, Moscow State Engineering Physics Institute (Russia)
Dmitry V. Repin, Moscow State Engineering Physics Institute (Russia)
Igor B. Scherbakov, Moscow State Engineering Physics Institute (Russia)
Rostislav S. Starikov, Moscow State Engineering Physics Institute (Russia)
Michael I. Zabulonov, Moscow State Engineering Physics Institute (Russia)

Published in SPIE Proceedings Vol. 2752:
Optical Pattern Recognition VII
David P. Casasent; Tien-Hsin Chao, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?