Share Email Print

Proceedings Paper

Recent progress in invariant pattern recognition
Author(s): Henri H. Arsenault; S. Chang; Philippe Gagne; Oscar Gualdron Gonzalez
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

We present some recent results in invariant pattern recognition, including methods that are invariant under two or more distortions of position, orientation and scale. There are now a few methods that yield good results under changes of both rotation and scale. Some new methods are introduced. These include locally adaptive nonlinear matched filters, scale-adapted wavelet transforms and invariant filters for disjoint noise. Methods using neural networks will also be discussed, including an optical method that allows simultaneous classification of multiple targets.

Paper Details

Date Published: 27 December 1996
PDF: 6 pages
Proc. SPIE 2969, Second International Conference on Optical Information Processing, (27 December 1996); doi: 10.1117/12.262620
Show Author Affiliations
Henri H. Arsenault, Univ. Laval (Canada)
S. Chang, Univ. Laval (Canada)
Philippe Gagne, Univ. Laval (Canada)
Oscar Gualdron Gonzalez, Univ. de Santander (Colombia)

Published in SPIE Proceedings Vol. 2969:
Second International Conference on Optical Information Processing
Zhores I. Alferov; Yuri V. Gulyaev; Dennis R. Pape, Editor(s)

© SPIE. Terms of Use
Back to Top