Texture feature extraction using co-occurrence matrices of sub-band image for batik image classification

In this study, we propose a new method to extract texture features of batik images. The proposed method is called co-occurrence matrices of sub-band images. This method is proposed to overcome the problem in classifying batik images that are acquired randomly from the internet. The problem of those images is the batik images contain various types of noise, such as unbalanced brightness, there are folds on fabrics images, the different size of basic motifs, low contrast, and there is watermark on the images. This method combines the advantages of gray-level co-occurrence matrices (GLCM) and discrete wavelet transform (DWT). First, the original image is decomposed using DWT to provide sub-band images. Second, GLCM is applied to sub-band images to extract the texture features. Those features will become the input for the probabilistic neural network (PNN). The results show that this method is robust enough to classify batik images. The maximum accuracy that can be achieved is 72%.