Abstract

A threshold is added to recognize an input pattern that has too few similarities to be one of the memory patterns. A real-time pattern recognition system based on the improved model is given. The unipolar optical pattern recognition system has all the characteristics of a fully bipolar winner-take-all model and has illumination invariance. A liquid-crystal spatial light modulator is used as a real-time input device, and a mask and a lens array perform the threshold and weighted sums of the input pattern. Some experimental results are also shown.

© 1994 Optical Society of America

Optoelectronic implementation of a fuzzy winner-take-all network for fuzzy logic inference

Shuqun Zhang and Caisheng Chen
Opt. Lett. 19(14) 1067-1069 (1994)

Optoelectronic thresholding module for winner-take-all operations in optical neural networks

Alain Bergeron, Henri H. Arsenault, Erik Eustache, and Denis Gingras
Appl. Opt. 33(8) 1463-1468 (1994)

Winner-take-all spatial light modulator

Timothy M. Slagle and Kelvin Wagner
Opt. Lett. 17(16) 1164-1166 (1992)

Optical competitive learning with VLSI/liquid-crystal winner-take-all modulators

Kelvin Wagner and Timothy M. Slagle
Appl. Opt. 32(8) 1408-1435 (1993)

Algorithm for optimizing bipolar interconnection weights with applications in associative memories and multitarget classification

Shengjiang Chang, Kwok-Wo Wong, Wenwei Zhang, and Yanxin Zhang
Appl. Opt. 38(23) 5032-5038 (1999)