earticle

영어

A new fabric defect detection algorithm base on Gabor filters is proposed. The spectral characteristics of both fabric texture and defects are analyzed. Gabor wavelet which can be considered as a bank of Gabor filters are used for the decomposition of fabric image. Based on spectral characteristics of fabric texture and defects, a new tuning method of Gabor wavelet is proposed to enhance the energy of defective region and attenuate the energy of normal texture. Decomposition images from different scales and orientations are fused into a single one to emphasize the presence of different kinds of defects. For comparison, the performance of proposed method as well as other two other defect detection methods using Gabor filters is evaluated with typical fabric defect samples. The experiment results obtained indicate that the proposed method is more effective than the other two.