Comparison Between Gabor Filters and Wavelets Transform for Classification of Textured Images

In the present research we have used wavelet transform and Gabor filters to extract texture features in order to classify textured-images. Gabor features are efficient in finding class boundaries, whereas the wavelets can represent textures at different scales and offer great discriminatory power between textures with strong resemblances. So, in this paper, we attempt to make a comparison between the feature extraction techniques based on Gabor filters and the wavelet transform with the purpose of classifying textured images. In the first step, we applied those two feature extraction strategies on textured images in order to get more information. After that in the second step, estimated feature vector of each pixel is sent to the neural networks classifier for labelling. The performance of the segmentation algorithms was evaluated on synthetic images from Brodatz and DTD datasets. The obtained classification results confirm the power of the wavelet transform features compared to Gabor filters features in classification of textured images.