Automatic fabric defect detection using optimal Gabor filter based on hybrid beetle antennae search-gravitational search algorithm

In this paper, a method for detecting defects in fabric surface is presented using an optimal Gabor filter based on hybrid BAS-GSA (Beetle Antennae Search Algorithm-Gravitational Search Algorithm). The method can be specifically divided into a training stage and a detection stage. Firstly, in training stage, a two-dimensional Gabor filter is constructed for defect-free fabric images. And then, the parameters of the Gabor filter are optimized using a combination model of BAS (Beetle Antennae Search Algorithm) and GSA (Gravitational Search Algorithm) with strong global and local search function. In the detection stage, a Gabor filter is constructed from the optimal parameters obtained in training stage, and the filter is used to convolve the fabric image to be detected; and then, the obtained convolution image is binarized to finally identify whether the fabric to be tested has defects. Experimental results show that the detection rate of this method can reach 98%, which has good stability and robustness, and is suitable for industrial production.