Detecting Defects in Textile Fabrics with Optimal Gabor Filters

detection scheme for solving the problem of automated defect detection for textile fabrics. In the development of the scheme, Gabor wavelet network (GWN) is deployed as the major technique to extract texture features from textile fabrics. An optimal Gabor filter is then designed on the basis of the features extracted. The proposed defect detection scheme consists of one real-valued optimal Gabor filter and one smoothing filter. The performance of the scheme is evaluated by using an offline test database with 78 homogeneous fabric images. The test results exhibit accurate defect detection with low false alarm, thus showing the effectiveness and robustness of the proposed scheme. The performance of the proposed scheme is further evaluated by conducting real time tests using a prototyped automated defect detection system. The experimental results obtained clearly demonstrate that the proposed scheme is indeed an effective and efficient means for detecting defects in textile fabrics.