Fabric Defect Detection Based on Local Entropy

Abstract

To solve the problem of automated defect detection for textile fabrics, this paper proposed a method for fabric defect detection which is based on local entropy. The method can transform the original gray image space for the entropy space and enhance the different organization structure which is conducive to extract the damage texture region. In the experiment, divided the fabric image to the same size local window, and chosen the smallest value of local entropy window region to segment the defects. The experimental result shown that this method can avoid the whole image complex operations and possess high recognition accuracy.