Within the textile manufacturing environment, inspection is an Importa
nt process which is employed in order to ensure high quality of the fi
nal products. Traditionally, this process is achieved manually which i
s very tedious, time consuming and labour intensive. A central problem
in automatic visual inspection and computer vision is to determine th
e extent to which one shape differs from another. This is the key elem
ent of any inspection algorithm. Pattern recognition operations such a
s correlation, template matching and model based vision methods can al
l be viewed as techniques for determining the difference between shape
s. In this paper the problem of visual inspection of deformable materi
als in general, and lace in particular, is considered. This is particu
larly difficult to achieve due to inherent and inevitable variations b
etween a 'model' and the material being inspected. A mechatronic appro
ach based on correlation along with morphological filters and 'active
vision in the loop' using a line-scan CCD camera is presented. The uti
lized algorithm and its advantages and disadvantages are also discusse
d. (C) 1998 Academic Press.