Share Email Print

Proceedings Paper

Template generation for pattern classification
Author(s): Paul D. Gader
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

A method for combining fuzzy morphological operations with fuzzy logic operations in a heterogeneous network structure is described. The first layer of the network would consist of template operations. The other layers would perform decision making. Such a network could be used to perform classification, image processing functions, and computer vision tasks. Generalized template operations are defmed using image algebra. It is shown that fuzzy morphological operations and linear operations can be obtained from the generalized operations by suitable choices of parameters. Training rules are described that can be used to "learn" the parameters of the generalized operations in a fashion similar to standard backpropagation. Thus, the network could learn linear or morphological operations, or a combination of the two.

Paper Details

Date Published: 1 June 1992
PDF: 10 pages
Proc. SPIE 1769, Image Algebra and Morphological Image Processing III, (1 June 1992); doi: 10.1117/12.60633
Show Author Affiliations
Paul D. Gader, Univ. of Missouri/Columbia (United States)

Published in SPIE Proceedings Vol. 1769:
Image Algebra and Morphological Image Processing III
Paul D. Gader; Edward R. Dougherty; Jean C. Serra, Editor(s)

© SPIE. Terms of Use
Back to Top