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

页码：85 / 109

页数：25

共 50 条

[21] Power Analysis Attack Based on GA-Based Ensemble Learning
Duan, Xiaoyi
Huang, Ye
Wang, Yuting
Gu, Yu
Tong, Jianmin
Wang, Zunyang
Hu, Ronglei
[J]. DIGITAL FORENSICS AND CYBER CRIME, PT 1, ICDF2C 2023, 2024, 570 : 308 - 322
[22] Unsupervised statistical neural networks for model-based object recognition
Kumar, VP
Manolakos, ES
[J]. IEEE TRANSACTIONS ON SIGNAL PROCESSING, 1997, 45 (11) : 2709 - 2718
[23] Robust hypothesis verification: application to model-based object recognition
Jurie, F
[J]. PATTERN RECOGNITION, 1999, 32 (06) : 1069 - 1081
[24] Model-based furniture recognition for building semantic object maps
Guenther, Martin
Wiemann, Thomas
Albrecht, Sven
Hertzberg, Joachim
[J]. ARTIFICIAL INTELLIGENCE, 2017, 247 : 336 - 351
[25] Combined model-based 3D object recognition
Kim, S
Jang, G
Lee, WH
Kweon, IS
[J]. INTERNATIONAL JOURNAL OF PATTERN RECOGNITION AND ARTIFICIAL INTELLIGENCE, 2005, 19 (07) : 839 - 852
[26] Boundary-coding technique for model-based object recognition
[J]. Ong, S.H., IEEE, Industrial Electronics Soc, New York, NY, USA; Univ of Tokyo, Inst of Industrial Science, Tokyo, Jpn; Information Processing Soc of Japan (IPSJ), Jpn; Inst of Electronics, Information and Communication Engineers of J; Japanese Soc for Artificial Intelligence (JSAI), Jpn; et al (Publ by IEEE, Piscataway, NJ, United States):
[27] Model-based occluded object recognition using Petri nets
Zhou, C
Hura, GS
[J]. AUTOMATIC TARGET RECOGNITION VIII, 1998, 3371 : 105 - 112
[28] MODEL-BASED OBJECT RECOGNITION USING BASIC PROBABILITY ASSIGNMENT
YAMANE, S
AOKI, K
IZUMI, M
FUKUNAGA, K
[J]. SYSTEMS AND COMPUTERS IN JAPAN, 1995, 26 (12) : 49 - 57
[29] MODEL-BASED OBJECT RECOGNITION USING A HIERARCHICAL NODE STRUCTURE
IZUMI, M
KAWAKAMI, H
AOKI, K
FUKUNAGA, K
[J]. INTERNATIONAL JOURNAL OF ELECTRONICS, 1993, 75 (05) : 795 - 810
[30] Using spatial sorting and ranking in model-based object recognition
Hjaltason, GR
Ray, M
Samet, H
Weiss, I
[J]. FOURTEENTH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION, VOLS 1 AND 2, 1998, : 1347 - 1349

← 1 2 3 4 5 →