Share Email Print

Proceedings Paper

A nonlinear training set superposition filter derived by neural network training methods for implementation in a shift-invariant optical correlator
Author(s): Ioannis Kypraios; Rupert C. D. Young; Philip M. Birch; Christopher R. Chatwin
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

The various types of synthetic discriminant function (sdf) filter result in a weighted linear superposition of the training set images. Neural network training procedures result in a non-linear superposition of the training set images or, effectively, a feature extraction process, which leads to better interpolation properties than achievable with the sdf filter. However, generally, shift invariance is lost since a data dependant non-linear weighting function is incorporated in the input data window. As a compromise, we train a non-linear superposition filter via neural network methods with the constraint of a linear input to allow for shift invariance. The filter can then be used in a frequency domain based optical correlator. Simulation results are presented that demonstrate the improved training set interpolation achieved by the non-linear filter as compared to a linear superposition filter.

Paper Details

Date Published: 6 August 2003
PDF: 12 pages
Proc. SPIE 5106, Optical Pattern Recognition XIV, (6 August 2003); doi: 10.1117/12.486334
Show Author Affiliations
Ioannis Kypraios, Univ. of Sussex (United Kingdom)
Rupert C. D. Young, Univ. of Sussex (United Kingdom)
Philip M. Birch, Univ. of Sussex (United Kingdom)
Christopher R. Chatwin, Univ. of Sussex (United Kingdom)

Published in SPIE Proceedings Vol. 5106:
Optical Pattern Recognition XIV
David P. Casasent; Tien-Hsin Chao, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?