Fabric defect detection based on Butterworth filters

A method for fabric defect detection based on Butterworth filters is proposed. A group of Butterworth filters with multi-scale and multi-orientation are designed based on the features of textured fabric with single color and simple structure. The fabric sample image is processed by the filter group, and filtered images are obtained which characterize the fabric defect in different orientations and scales in the frequency domain. These filtered images are binarized and then fused in order to reconstruct the binary output image that separates the defect from the texture background. Experiment results have confirmed the effectiveness and adaptability of the proposed method for fabric defect detection.