Abstract
A compact neural network architecture is described that can be trained to sense and classify an optical image directly projected onto it. The system is based on the combination of a two-dimensional amorphous silicon photoconductor array and a liquid-crystal spatial light modulator. Appropriate filtering of the incident optical image on capture is incorporated into the network training rules through a modification of the standard backpropagation training algorithm. Training of the network on two image-classification problems is described: the recognition of handprinted digits and facial recognition. The network, once trained, is capable of stand-alone operation, sensing an incident image, and outputting a final classification signal in real time.
© 1995 Optical Society of America
Full Article | PDF ArticleMore Like This
Richard G. Stearns
Appl. Opt. 32(26) 5141-5152 (1993)
Richard G. Stearns
Appl. Opt. 31(29) 6230-6239 (1992)
Lennart A. Saaf and G. Michael Morris
Appl. Opt. 34(20) 3963-3970 (1995)