Abstract

A novel neural-network architecture that combines image data reduction with focus of attention to achieve reduced training cost, improved noise tolerance, and better generalization performance than comparable conventional networks for image-recognition tasks is presented. The dual-scale architecture is amenable to optical implementation, and an example optical system is demonstrated. For one example problem, the best-case improvements of the dual-scale network over its conventional counterpart were found through simulation to be a factor of 6.7 in training cost, 67.3% in noise tolerance, and 61.6% in generalization to distortions. The dual-scale network is also applied to one instance of a human face recognition problem.

© 1995 Optical Society of America

Adaptive, optical, radial basis function neural network for handwritten digit recognition

Wesley E. Foor and Mark A. Neifeld
Appl. Opt. 34(32) 7545-7555 (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)

Face recognition by using feature-specific imaging

Himadri S. Pal, Dinesh Ganotra, and Mark A. Neifeld
Appl. Opt. 44(18) 3784-3794 (2005)

Neural network pattern recognition of thermal-signature spectra for chemical defense

Arthur H. Carrieri and Pascal I. Lim
Appl. Opt. 34(15) 2623-2635 (1995)