The automated inspection of lace using machine vision

Abstract

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 Sparc 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.