Share Email Print
cover

Proceedings Paper

Wilson-Cowan neural network in image analysis
Author(s): Kari Mantere; Jussi P. S. Parkkinen; Timo Jaeaeskelaeinen; Madan M. Gupta
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

The neural network model based on the theory proposed by Wi1son—owan has been simulated using digitized real images. The Wilson—Cowan net can operate in different modes depending on the parameter selection, and it is shown to store images in reduced form and to recognize edges of object. Examples how the net process the input images are shown. Due to large number of neurons in this model, the preferable technique to simulate it should be parallel processing one. Optics serve highly parallelism and we propose a basic hybrid—optical processing unit for the Wilson—Cowan net.

Paper Details

Date Published: 1 April 1992
PDF: 8 pages
Proc. SPIE 1658, Nonlinear Image Processing III, (1 April 1992); doi: 10.1117/12.58388
Show Author Affiliations
Kari Mantere, Univ. of Kuopio (Finland)
Jussi P. S. Parkkinen, Univ. of Kuopio (Finland)
Timo Jaeaeskelaeinen, Univ. of Joensuu (Finland)
Madan M. Gupta, Univ. of Saskatchewan (Canada)


Published in SPIE Proceedings Vol. 1658:
Nonlinear Image Processing III
Edward R. Dougherty; Jaakko T. Astola; Charles G. Boncelet, Editor(s)

© SPIE. Terms of Use
Back to Top