Share Email Print

Optical Engineering

Entropy optimized morphological shared-weight neural networks
Author(s): Mohamed A. Khabou; Paul D. Gader; Hongchi Shi
Format Member Price Non-Member Price
PDF $20.00 $25.00

Paper Abstract

Morphological shared-weight neural networks previously demonstrated performance superior to that of MACE filters and standard shared-weight neural networks for target detection. Empirical analysis showed that entropy measures of the morphological shared-weight networks were consistently higher than those of the standard shared-weight neural networks. Based on this observation, an entropy maximization term was added to the morphological shared-weight network objective function. In this paper, target detection results are presented for morphological shared-weight networks trained with and without entropy terms.

Paper Details

Date Published: 1 February 1999
PDF: 11 pages
Opt. Eng. 38(2) doi: 10.1117/1.602085
Published in: Optical Engineering Volume 38, Issue 2
Show Author Affiliations
Mohamed A. Khabou, Univ. of Missouri/Columbia (United States)
Paul D. Gader, Univ. of Missouri/Columbia (United States)
Hongchi Shi, Univ. of Missouri/Columbia (United States)

© SPIE. Terms of Use
Back to Top