GA-based learning for a model-based object recognition system

被引：8
作者：
Soodamani, R [1 ]
Liu, ZQ [1 ]
机构：
[1] Univ Melbourne, Dept Comp Sci, CVMIL, Carlton, Vic 3053, Australia
来源：
INTERNATIONAL JOURNAL OF APPROXIMATE REASONING | 2000年 / 23卷 / 02期
关键词：
model based object recognition; range images; fuzzy attributes; learning; genetic algorithm; performance enhancement;
D O I：
10.1016/S0888-613X(99)00036-5
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
This paper proposes a genetic-algorithm-based learning strategy that models membership functions of the fuzzy attributes of surfaces in a model based machine vision system. The objective function aims at enhancing recognition performance in terms of maximizing the degree of discrimination among classes. As a result, the accuracy of recognizing known instances of objects and generalization capability by recognizing unknown instances of known objects are greatly improved. Performance enhancement is achieved by incorporating an off-line learning mechanism using genetic algorithm in the feedback path of the recognition system. (C) 2000 Elsevier Science Inc. All rights reserved.
引用
收藏
页码：85 / 109
页数：25
相关论文
共 29 条
[1]  
ABE S, 1992, IEEE T FUZZY SYST, V1, P18
[2]  
[Anonymous], 1989, GENETIC ALGORITHM SE
[3]  
[Anonymous], 1981, GENETIC ALGORITHMS F
[4]  
Baker J. E., 1987, Genetic Algorithms and their Applications: Proceedings of the Second International Conference on Genetic Algorithms, P14
[5]  
BESL BP, 1986, COMPUTER VISION PATT, P195
[6]   INVARIANT SURFACE CHARACTERISTICS FOR 3D OBJECT RECOGNITION IN RANGE IMAGES [J].
BESL, PJ ;
JAIN, RC .
COMPUTER VISION GRAPHICS AND IMAGE PROCESSING, 1986, 33 (01) :33-80
[7]  
Brindle A., 1981, THESIS U ALBERTA
[8]   VARIATIONS ON THE EVIDENCE-BASED OBJECT RECOGNITION THEME [J].
CAELLI, T ;
DREIER, A .
PATTERN RECOGNITION, 1994, 27 (02) :185-204
[9]  
De Jong K. A., 1975, ANAL BEHAV CLASS GEN
[10]   The use of multiple measurements in taxonomic problems [J].
Fisher, RA .
ANNALS OF EUGENICS, 1936, 7 :179-188
123