A method of image analysis is proposed for detection of local defects
in materials with periodic regular texture. A general improvement and
enlargement of vision system capabilities for versatility, full automa
tism, computational efficiency, and robustness in their application to
the industrial inspection of periodic textured materials is pursued.
In the proposed method, a multiscale and multiorientation Gabor filter
scheme that imitates the early human vision process is applied to the
sample under inspection. The designed algorithm automatically segment
s defects from the regular texture. A variety of examples of fabric in
spection are presented. In all of them defects are successfully segmen
ted from the texture background. (C) 1998 Society of Photo-Optical Ins
trumentation Engineers.