27 March 1995 Machine vision inspection of lace using a neural network
Author Affiliations +
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. Small distortions in the pattern are unavoidable. This paper describes instrumentation for inspecting lace actually on the knitting machine. A CCD linescan camera synchronized 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.
© (1995) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Christopher Sanby, Leonard Norton-Wayne, "Machine vision inspection of lace using a neural network", Proc. SPIE 2423, Machine Vision Applications in Industrial Inspection III, (27 March 1995); doi: 10.1117/12.205518; https://doi.org/10.1117/12.205518


System for inspecting color printing quality: ARGUS
Proceedings of SPIE (October 10 1994)
Integrated machine vision technology for line-scan applications
Proceedings of SPIE (September 18 1997)
Neural networks for web-process inspection
Proceedings of SPIE (September 02 1993)
Finish inspection by vision for glass production
Proceedings of SPIE (March 11 1994)
Quality control in tile production
Proceedings of SPIE (October 06 1998)

Back to Top