Share Email Print

Proceedings Paper

Filter Synthesis Using Neural Networks
Author(s): Lennart A. Saaf; G. Michael Morris
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

We are investigating an opto-electronic implementation of a trainable pattern classification system based on a feed-forward neural network model. An architecture with two layers of interconnections is used to transform a large amount of scene information to a small feature space that is, in turn, transformed into classification data. By using two layers of interconnections the number of large inner products that must be calculated may be significantly reduced. Simulations have been performed on a digital computer that demonstrate the performance of a system for the rotation-invariant classification of printed characters. A possible optical implementation is outlined.

Paper Details

Date Published: 25 October 1989
PDF: 5 pages
Proc. SPIE 1134, Optical Pattern Recognition II, (25 October 1989); doi: 10.1117/12.961608
Show Author Affiliations
Lennart A. Saaf, University of Rochester (United States)
G. Michael Morris, University of Rochester (United States)

Published in SPIE Proceedings Vol. 1134:
Optical Pattern Recognition II
H. John Caulfield, Editor(s)

© SPIE. Terms of Use
Back to Top