Share Email Print
cover

Proceedings Paper

Shift-invariant neural network for image processing: learning and generalization
Author(s): Wei Zhang; Akira Hasegawa; Osamu Matoba; Kazuyoshi Itoh; Yoshiki Ichioka; Kunio Doi
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

We have applied a shift-invariant back propagation neural network to the cells' boundary detection of human corneal endothelium photomicrographs. The interconnection patterns of the neural network are constrained to be spatially invariant. Our experiments demonstrated that the generalizing ability of the neural network is dependent on its connectivity or complexity, i.e., the number of connections. To get a better generalization, we have proposed a modified back propagation learning rule, which reduces the complexity of the neural network during the learning procedure. The measure of the complexity of the neural network was defined as a formal entropy of the connectivity pattern. Simulations showed that the neural network trained by this learning rule has better generalizing ability but more computational complexity. In this paper a simplified function is investigated as the measure of the complexity of the neural network. This simplified measure is a first order approximation of the formal entropy measure. Simulations show that the simplified measure is effective to get better generalization and has less computational complexity than the original formal entropy measure.

Paper Details

Date Published: 16 September 1992
PDF: 12 pages
Proc. SPIE 1709, Applications of Artificial Neural Networks III, (16 September 1992); doi: 10.1117/12.140004
Show Author Affiliations
Wei Zhang, Kurt Rossmann Labs. for Radiological Image Research/Univ. of Chicago (United States)
Akira Hasegawa, Osaka Univ. (Japan)
Osamu Matoba, Osaka Univ. (Japan)
Kazuyoshi Itoh, Osaka Univ. (Japan)
Yoshiki Ichioka, Osaka Univ. (Japan)
Kunio Doi, Kurt Rossmann Labs. for Radiological Image Research/Univ. of Chicago (United States)


Published in SPIE Proceedings Vol. 1709:
Applications of Artificial Neural Networks III
Steven K. Rogers, Editor(s)

© SPIE. Terms of Use
Back to Top