Share Email Print

Proceedings Paper

Adaptive-optical radial-basis-function neural network for handwritten digit recognition
Author(s): Wesley E. Foor; Mark Allen Neifeld
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

An adaptive optical radial basis function classifier for handwritten digit recognition is experimentally demonstrated. We describe a spatially- multiplexed system incorporating 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 and 198 stored reference patterns in parallel using dual vector-matrix multipliers. For this experimental software is used to perform the on-line learning of the weights and basis function widths. An experimental recognition rate of 86.7% correct out of 300 testing samples is achieved with the adaptive training versus 52.3% correct for non-adaptive training. The experimental results from the optical system are compared with data from a computer model of the system in order to identify noise sources and indicate possible improvements for system performance.

Paper Details

Date Published: 29 June 1994
PDF: 9 pages
Proc. SPIE 2240, Advances in Optical Information Processing VI, (29 June 1994); doi: 10.1117/12.179121
Show Author Affiliations
Wesley E. Foor, Univ. of Arizona and Rome Lab. (United States)
Mark Allen Neifeld, Univ. of Arizona (United States)

Published in SPIE Proceedings Vol. 2240:
Advances in Optical Information Processing VI
Dennis R. Pape, Editor(s)

© SPIE. Terms of Use
Back to Top