Optimal morphological filter design for fabric defect detection

This paper investigates the problem of automated defect detection for textile fabrics and proposes a new optimal morphological filter design method for solving this problem. Gabor Wavelet Network (GWN) is adopted as a major technique to extract the texture features of textile fabrics. An optimal morphological filter can be constructed based on the texture features extracted. In view of this optimal filter, a new semi-supervised segmentation algorithm is then proposed. The performance of the scheme is evaluated by using a variety of homogeneous textile images with different types of common defects. The test results exhibit accurate defect detection with low false alarm, thus confirming the robustness and effectiveness of the proposed scheme. In addition, it can be shown that the algorithm proposed in this paper is suitable for on-line applications. Indeed, the proposed algorithm is a low cost PC based solution to the problem of defect detection for textile fabrics. © 2005 IEEE.published_or_final_versio