Share Email Print

Optical Engineering

Optoelectronic neural filtering of contour figure features
Author(s): Andrei L. Mikaelian; Victor A. Ivanov; Boris S. Kiselyov
Format Member Price Non-Member Price
PDF $20.00 $25.00

Paper Abstract

Image preprocessing aimed at recognizing pattern fragments is considered. Problems of constructing homogeneous neural networks capable of selecting simple features of contour figures are studied. The filtration and selection of pattern fragments, such as line intersections, line ends, fractures, etc., are shown to be effectively accomplished by optical means.

Paper Details

Date Published: 1 August 1996
PDF: 4 pages
Opt. Eng. 35(8) doi: 10.1117/1.600822
Published in: Optical Engineering Volume 35, Issue 8
Show Author Affiliations
Andrei L. Mikaelian, Inst. of Optical Neural Tech. (Russia)
Victor A. Ivanov, Institute of Optical Neural Technologies (Russia)
Boris S. Kiselyov, Institute of Optical Neural Technologies (Russia)

© SPIE. Terms of Use
Back to Top