Abstract

An adaptive, optical, radial basis function classifier for handwritten digit recognition is experimentally demonstrated. We describe a spatially multiplexed system that incorporates an on-line adaptation of weights and basis function widths to provide robustness to optical system imperfections and system noise. The optical system computes the Euclidean distances between a 100-dimensional input vector and 198 stored reference patterns in parallel by using dual vector–matrix multipliers and a contrast-reversing spatial light modulator. Software is used to emulate an electronic chip that performs the on-line learning of the weights and basis function widths. An experimental recognition rate of 92.7% correct out of 300 testing samples is achieved with the adaptive training, versus 31.0% correct for nonadaptive training. We compare the experimental results with a detailed computer model of the system in order to analyze the influence of various noise sources on the system performance.

© 1995 Optical Society of America

Optical implementations of radial basis classifiers

Mark A. Neifeld and Demetri Psaltis
Appl. Opt. 32(8) 1370-1379 (1993)

64-channel correlator implementing a Kohonen-like neural network for handwritten-digit recognition

M. Barge, K. Heggarty, Y. Idan, and R. Chevallier
Appl. Opt. 35(23) 4655-4665 (1996)

Optical dual-scale architecture for neural image recognition

Mark A. Neifeld
Appl. Opt. 34(26) 5920-5927 (1995)

Optical implementation of neural networks for face recognition by the use of nonlinear joint transform correlators

Bahram Javidi, Jian Li, and Qing Tang
Appl. Opt. 34(20) 3950-3962 (1995)

Neural network that incorporates direct optical imaging

Richard G. Stearns
Appl. Opt. 34(14) 2595-2604 (1995)