Share Email Print

Proceedings Paper

Nonlinear features for improved pattern recognition
Author(s): David P. Casasent; Ashit Talukder
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

Nonlinear features that represent higher-order correlations in input data are considered for improved recognition. They optimize new performance measures that do not make Gaussian etc. data distribution assumptions and that are intended for improved discrimination. The new features are produced in closed-form and are thus preferable to iterative solutions. An efficient two-step feature extraction algorithm is presented for the high-dimensional (iconic) input data case of most interest. The feature generation can be realized as a new neural network with adaptive activation functions. Test results on pose-invariant face recognition are emphasized; results on standard feature inputs for a product inspection application are briefly noted as a low- dimensional input data case.

Paper Details

Date Published: 6 July 2001
PDF: 9 pages
Proc. SPIE 4392, Optical Processing and Computing: A Tribute to Adolf Lohmann, (6 July 2001); doi: 10.1117/12.432795
Show Author Affiliations
David P. Casasent, Carnegie Mellon Univ. (United States)
Ashit Talukder, Jet Propulsion Lab. (United States)

Published in SPIE Proceedings Vol. 4392:
Optical Processing and Computing: A Tribute to Adolf Lohmann
David P. Casasent; H. John Caulfield; William J. Dallas; Harold H. Szu, Editor(s)

© SPIE. Terms of Use
Back to Top