Adaptive surface inspection via interactive evolution

被引:44
作者
Caleb-Solly, P. [1 ]
Smith, J. E. [1 ]
机构
[1] Univ W England, Fac Comp Engn & Math Sci, Bristol BS16 1QY, Avon, England
关键词
machine vision; configuration; interative; evolution;
D O I
10.1016/j.imavis.2006.04.023
中图分类号
TP18 [人工智能理论];
学科分类号
081104 [模式识别与智能系统]; 0812 [计算机科学与技术]; 0835 [软件工程]; 1405 [智能科学与技术];
摘要
An increasingly frequent application of Machine Vision technologies is in automated surface inspection for the detection of defects in manufactured products. Such systems offer significant benefits in terms of cost, detection rates, and user-satisfaction over conventional human inspection systems. However, they usually require significant investment of expert time to set up, are "brittle" in the sense of being highly specialised to the task for which they are tuned, and are consequently sensitive to changes in operating conditions or product specifications. This raises problems within an industrial setting, where operating conditions or requirements may change, and the end-users are experts in their manufacturing field, but not in image processing. In this paper, we describe the development of a rapidly reconfigurable system in which the users' tacit knowledge and requirements are elicited via a process of Interactive Evolution, finding the image processing parameters to achieve the required goals without any need for specialised knowledge of the machine vision system. We show that the resulting segmentation can be quickly and easily evolved from scratch, and achieves detection rates comparable to those of a hand-tuned system on a hot-rolled steel defect recognition problem. (C) 2007 Published by Elsevier B.V.
引用
收藏
页码:1058 / 1072
页数:15
相关论文
共 15 条
[1]
ALOCK R, 2004, ARTIFICIAL INTELLIGE
[2]
Back T., 1991, P 4 INT C GEN ALG, P2
[3]
BILES JA, 1994, ICMC P
[4]
BRODATZ P, 1966, PHOTOGRAPHIC ALBUM A
[5]
CALEB P, P IEEE 4 INT C KNOWL, V1, P103, DOI UNSP 0-7803-6400-7
[6]
CALEBSOLLY P, 2004, P 6 INT C AD COMP DE
[7]
DAWKINS R, 1987, BLIND WATCHMAKER
[8]
EIBEN AE, 2003, INTRO EVOLUTIONARY
[9]
Soft computing for automated surface quality analysis of exterior car body panels [J].
Eichhorn, A ;
Girimonte, D ;
Klose, A ;
Kruse, R .
APPLIED SOFT COMPUTING, 2005, 5 (03) :301-313
[10]
TEXTURAL FEATURES FOR IMAGE CLASSIFICATION [J].
HARALICK, RM ;
SHANMUGAM, K ;
DINSTEIN, I .
IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS, 1973, SMC3 (06) :610-621