Application of Contourlet Transform for Fabric Defect Detection

In this paper Contourlet based statistical modeling is used for Fabric Defect Detection. The Contourlet transform is a recently proposed two dimensional method used for image analysis. It is very efficient for representing images with fine geometrical structure. In the proposed method for defect detection Contourlet based feature extraction is used. Contourlet Transform is capable of capturing the smooth edges information. A new filter bank structure is the Contourlet filter bank that can provide a flexible multiscale and directional decomposition for images. Specifically, a discrete-domain multiresolution and multi direction expansion using non-separable filter banks, in much the same way those wavelets were derived from filter banks. This construction results in a flexible multiresolution, local, and directional image expansion using contour segments, and thus it is named the Contourlet Transform. Edges are image points with discontinuity, whereas contours are edges that are localized and regular. So Contourlet can be defined as a multi-scale, local and directional contour segment which can be constructed using filter banks. Contourlet transform can be used for the detection of defect in fabric. If there is defect in fabric its price reduces so it is very important to detect defect in fabric.