Abstract

A simple optoelectronic architecture is defined with capabilities of matching a test image (1-D or 2-D) with stored images. It is shown that if a test image and a complementary stored image together with complementary test image and stored image are compared optically, the emerging light intensity is minimum for the best match (i.e., shortest Hemming distance). This allows the suggested architecture to do efficient parallel comparison and to point out the best matched test image. If the image is presented in a two color scheme (say red–blue) and the memory images are stored in the complimentary color scheme transparency (i.e., blue–red), then a white light source allows comparison and detection of best matched image without the need for a separate set of complimentary images. A time-varying light intensity (or a time-varying thresholding voltage) source and an integrating-threshold device which switches its state when light input falls below a threshold value are two ingredients, which are used to select the best match in parallel. Grey level detection can also be implemented by the scheme. The architecture is also ideally suited to finding the closeness of match of two images.

© 1990 Optical Society of America

Evaluation and improvement of associative memory for pattern recognition

Junichi Homma, Yukio Kosugi, and Takuso Sato
Appl. Opt. 29(11) 1675-1681 (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)

Projection method formulations of Hopfield-type associative memory neural networks

M. Ibrahim Sezan, Henry Stark, and Shu-Jen Yeh
Appl. Opt. 29(17) 2616-2622 (1990)

Optoelectronic-cache memory system architecture

Donald M. Chiarulli and Steven P. Levitan
Appl. Opt. 35(14) 2449-2456 (1996)

Ho-Kashyap optical associative processors

Brian Telfer and David P. Casasent
Appl. Opt. 29(8) 1191-1202 (1990)