THE AUTOMATED INSPECTION OF LACE USING MACHINE VISION

被引:31
作者
SANBY, C [1 ]
NORTONWAYNE, L [1 ]
HARWOOD, R [1 ]
机构
[1] DE MONTFORT UNIV,DEPT TEXT & FASH,LEICESTER LE1 9BH,LEICS,ENGLAND
关键词
D O I
10.1016/0957-4158(95)00012-T
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Lace is particularly difficult to inspect using machine vision since it comprises a fine and complex pattern of threads which must be verified, on line and in real time. This paper describes instrumentation for inspecting lace actually on the knitting machine. A CCD linescan camera, synchronised to machine motions, grabs an image of the lace. Differences between this lace image and a perfect prototype image are detected by comparison methods, thresholding techniques, and finally, a neural network (to distinguish real defects from false alarms). Though produced originally in a laboratory on SUN Spare work-stations, the processing has subsequently been implemented on a 50 MHz 486 PC look-alike. Successful operation has been demonstrated in a factory, but over a restricted width. Full width coverage awaits provision of faster processing.
引用
收藏
页码:215 / 231
页数:17
相关论文
共 6 条
[1]  
Caudill M., 1992, UNDERSTANDING NEURAL
[2]  
LEE Y, 1991, P INT JOINT C NEUR N, V1, P765
[3]  
MICHAELS DF, 1990, P IEEE C SYSTEMS MAN, P41
[4]  
Norton-Wayne L., 1991, Computer Graphics Forum, V10, P113, DOI 10.1111/1467-8659.1020113
[5]  
NORTONWAYNE L, 1982, THESIS CITY U LONDON
[6]  
NORTONWAYNE L, 1993, P SOC PHOTO-OPT INS, P1