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.
%0 Journal Article
%1 Sanby1995215
%A Sanby, C.
%A Norton-Wayne, L.
%A Harwood, R.
%D 1995
%E NN,
%J Mechatronics
%K automated inspection lace machine vision
%N 2–3
%P 215 - 231
%R http://dx.doi.org/10.1016/0957-4158(95)00012-T
%T The automated inspection of lace using machine vision
%U http://www.sciencedirect.com/science/article/pii/095741589500012T
%V 5
%X 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.
@article{Sanby1995215,
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. },
added-at = {2014-10-19T16:44:20.000+0200},
author = {Sanby, C. and Norton-Wayne, L. and Harwood, R.},
biburl = {https://www.bibsonomy.org/bibtex/262fd842177374c7cbba7d39b0ffbb232/kinski1810},
doi = {http://dx.doi.org/10.1016/0957-4158(95)00012-T},
editor = {NN},
interhash = {ed0cfe6181a0568613f2833afc8db2e1},
intrahash = {62fd842177374c7cbba7d39b0ffbb232},
issn = {0957-4158},
journal = {Mechatronics },
keywords = {automated inspection lace machine vision},
note = {Mechatronics in Textfile Industries },
number = {2–3},
pages = {215 - 231},
timestamp = {2014-10-19T16:44:20.000+0200},
title = {The automated inspection of lace using machine vision },
url = {http://www.sciencedirect.com/science/article/pii/095741589500012T},
volume = 5,
year = 1995
}