Share Email Print
cover

Proceedings Paper

Application of optoelectronic neural networks to the selection of contour figure features
Author(s): Victor A. Ivanov; Boris S. Kiselyov; Andrei L. Mikaelian
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

Homogeneous optical neural networks are used in the filtration and selection of pattern fragments, such as line intersections, line ends, fractures, etc. The approach proposed allows us to develop simple neural nets with virtually any form of receptive fields. The processing method is suggested in which only those simple features survive that have specific relative positions.

Paper Details

Date Published: 27 December 1996
PDF: 6 pages
Proc. SPIE 2969, Second International Conference on Optical Information Processing, (27 December 1996); doi: 10.1117/12.262568
Show Author Affiliations
Victor A. Ivanov, Institute of Optical Neural Technologies (Russia)
Boris S. Kiselyov, Institute of Optical Neural Technologies (Russia)
Andrei L. Mikaelian, Institute of Optical Neural Technologies (Russia)


Published in SPIE Proceedings Vol. 2969:
Second International Conference on Optical Information Processing
Zhores I. Alferov; Yuri V. Gulyaev; Dennis R. Pape, Editor(s)

© SPIE. Terms of Use
Back to Top