Share Email Print

Proceedings Paper

Classification of noisy patterns using ARTMAP-based neural networks
Author(s): Dimitrios Charalampidis; Georgios C. Anagnostopoulos; Takis Kasparis; Michael Georgiopoulos
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

In this paper we present a modification of the test phase of ARTMAP-based neural networks that improves the classification performance of the networks when the patterns that are used for classification are extracted from noisy signals. The signals that are considered in this work are textured images, which are a case of 2D signals. Two neural networks from the ARTMAP family are examined, namely the Fuzzy ARTMAP (FAM) neural network and the Hypersphere ARTMAP (HAM) neural network. We compare the original FAM and HAM architectures with the modified ones, which we name FAM-m and HAM-m respectively. We also compare the classification performance of the modified networks, and of the original networks when they are trained with patterns extracted from noisy textures. Finally, we illustrate how combination of features can improve the classification performance for both the noiseless and noisy textures.

Paper Details

Date Published: 29 June 2000
PDF: 12 pages
Proc. SPIE 4041, Visual Information Processing IX, (29 June 2000); doi: 10.1117/12.390470
Show Author Affiliations
Dimitrios Charalampidis, Univ. of Central Florida (United States)
Georgios C. Anagnostopoulos, Univ. of Central Florida (United States)
Takis Kasparis, Univ. of Central Florida (United States)
Michael Georgiopoulos, Univ. of Central Florida (United States)

Published in SPIE Proceedings Vol. 4041:
Visual Information Processing IX
Stephen K. Park; Zia-ur Rahman, Editor(s)

© SPIE. Terms of Use
Back to Top