For this project, we explored many approaches to perform supervised texture segmentation.The main idea is 
to feed multiple machine learning algorithms with state of the art texture descriptors. The texture features
are extracted by using Empirical Wavelet Transform. We build a unique empirical curvelet filter bank adapted
to a given dictionary of textures. We then show that the output of these filters can be used to build efficient
texture descriptors utilized to finally feed machine learning classifiers. Our approach is evaluated on a 
grayscale dataset and compared the results to various algorithms to show that the proposed methods perform
comparably or better to naively implemented neural networks.