random texture defect detection by modeling the extracted features from the optimal gabor filter

in this paper, a new method is presented for the detection of defects in random textures. in the training stage, the feature vectors of the normal textures’ images are extracted by using the optimal response of gabor wavelet filters, and their probability density is estimated by means of the gaussian mixture model (gmm). in the testing stage, similar to the previous stage,at  first, the feature vectors corresponding to local neighborhoods of each pixel of the image under inspection are extracted. then, by computing the likelihood of the test image’s feature vectors’ belonging to the parameters of the gmm, they are compared with a threshold value. finally, the defective regions are localized in a defect map. the proposed algorithm was evaluated on a set of grayscale ceramic tile images with random textures. the simulations indicate that in comparison with the previous methods, the proposed algorithm enjoys an acceptable computational volume and accuracy in the detection of texture defects.