Abstract

An optoneural system, which is a combination of an optical processor and a neural network, is developed for pattern classification. The system takes advantages of the two-dimensional processing capability of optics and the mapping capability of neural networks. The optical processor consists of a binary phase-only filter, and the neural network consists of three nonlinear mapping layers: the input layer, a hidden layer, and the output layer. Correlation outputs of the optical processor are used as inputs to the neural network. Binary phase in the binary phase-only filter and weights of the neural network are simultaneously trained with a simulated annealing algorithm. Gray-tone texture patterns that are not easily classified with annealed binary phase-only filters are well classified with the trained optoneural system.

© 1990 Optical Society of America