Singular value decomposition for texture defect detection in visual inspection systems

In this paper the authors propose an algorithm for texture defects detection, which doesn´t use supervised classification. The algorithm can be simply applied in an automatic visual inspection system. For localization of texture defects features calculation of each non-overlapping region of an image via the singular value decomposition (SVD) and image processing techniques. In next step the algorithm uses the fuzzy c-means clustering (FCM) to classify each region into two clusters. Finally the authors define a distance between centres of defective and non-defective clusters using some threshold value chosen empirically