Entropy optimized morphological shared-weight neural networks

被引：12

作者：

Khabou, MA ^{[1
]}

Gader, PD ^{[1
]}

Shi, HC ^{[1
]}

机构：

[1] Univ Missouri, Columbia, MO 65211 USA

来源：

OPTICAL ENGINEERING | 1999年 / 38卷 / 02期

关键词：

entropy; morphological shared-weight nets; ATR; SAR; MSTAR;

D O I：

10.1117/1.602085

中图分类号：

O43 [光学];

学科分类号：

070207 ; 0803 ;

摘要：

Morphological shared-weight neural networks previously demonstrated performance superior to that of MACE fitters 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. (C) 1999 Society of Photo-Optical Instrumentation Engineers. [S0091-3286(99)00502-4].

引用

页码：263 / 273

页数：11

共 10 条

[1] DOUGHERTY ER, 1992, INTRO MORPHOLOGICAL
[2] GADER PD, 1994, P SOC PHOTO-OPT INS, V2300, P157, DOI 10.1117/12.179187
[3] Segmentation free shared weight networks for automatic vehicle detection
Gader, PD
Miramonti, JR
Won, Y
Coffield, P
[J]. NEURAL NETWORKS, 1995, 8 (09) : 1457 - 1473
[4] Automatic feature generation for handwritten digit recognition
Gader, PD
Khabou, MA
[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1996, 18 (12) : 1256 - 1261
[5] ON THE RATIONALE OF MAXIMUM-ENTROPY METHODS
JAYNES, ET
[J]. PROCEEDINGS OF THE IEEE, 1982, 70 (09) : 939 - 952
[6] Backpropagation Applied to Handwritten Zip Code Recognition
LeCun, Y.
Boser, B.
Denker, J. S.
Henderson, D.
Howard, R. E.
Hubbard, W.
Jackel, L. D.
[J]. NEURAL COMPUTATION, 1989, 1 (04) : 541 - 551
[7] LECUN Y, 1990, P 1 INT WORKSH FRONT
[8] Mensa D. L., 1991, High Resolution Radar Cross-Section Imaging
[9] Detection and classification of MSTAR objects via morphological shared-weight neural networks
Theera-Umpon, N
Khabou, MA
Gader, PD
Keller, JM
Shi, HC
Li, HZ
[J]. ALGORITHMS FOR SYNTHETIC APERTURE RADAR IMAGERY V, 1998, 3370 : 530 - 540
[10] Morphological shared-weight networks with applications to automatic target recognition
Won, YG
Gader, PD
Coffield, PC
[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS, 1997, 8 (05): : 1195 - 1203

← 1 →