Automatic visual inspection has become one of the active research issu
es in machine vision technology in the past decades. Most of the metho
dologies developed address the problems of defect detection on a nonte
xtured or regularly textured surface. However, problems in detecting d
efects on a randomly textured surface, especially cracks, have not rec
eived much attention. In this paper, we present a novel algorithm that
uses a Wigner model to identify cracks in complex textural background
s, regardless of whether the inspected surface is randomly or regularl
y textured. We also investigate the windowing characteristics of the W
igner distribution and their impact on crack detection. Some of the Br
odatz' natural texture images have been used for evaluating the perfor
mance of the algorithm. Promising results are obtained and presented i
n this paper.