Abstract

Optical systems of associative memory models are capable of reconstructing lost information from incomplete input patterns. In this paper, we evaluate the ability of associative memory models when used in practical pattern recognition systems. Effects of improvement techniques, including defocusing preprocessing, and the recursive use of the associative operation are also examined with computer simulations. Finally the effectiveness of the recognition system is tested experimentally with alphabetic characters in different illumination conditions.

© 1990 Optical Society of America

Optoelectronic architecture for associative memory applicable to 2-D pattern comparison

Jasprit Singh and Songcheol Hong
Appl. Opt. 29(11) 1682-1688 (1990)

Experimental studies on learning capabilities of optical associative memory

Masatoshi Ishikawa, Naohisa Mukohzaka, Haruyoshi Toyoda, and Yoshiji Suzuki
Appl. Opt. 29(2) 289-295 (1990)

Adaptive optical processing system with optical associative memory

Haruyoshi Toyoda, Naohisa Mukohzaka, Yoshiji Suzuki, and Masatoshi Ishikawa
Appl. Opt. 32(8) 1354-1358 (1993)

Interference filters as nonlinear decision-making elements for three-spot pattern recognition and associative memories

L. Wang, V. Esch, R. Feinleib, L. Zhang, R. Jin, H. M. Chou, Robert W. Sprague, H. Angus Macleod, G. Khitrova, Hyatt M. Gibbs, Kelvin Wagner, and Demetri Psaltis
Appl. Opt. 27(9) 1715-1720 (1988)

Optical pattern recognition and associative memory: an introduction by the feature editor

Hua-Kuang Liu
Appl. Opt. 28(2) 217-218 (1989)