Empirical curvelet based Fully Convolutional Network for supervised texture image segmentation
This addresses texture segmentation for computer vision applications, representing an incremental improvement through hybrid feature engineering.
The paper tackles supervised texture image segmentation by feeding a Fully Convolutional Network with texture descriptors extracted via an empirical curvelet transform adapted to a texture dictionary. The method dramatically outperforms state-of-the-art algorithms on several datasets.
In this paper, we propose a new approach to perform supervised texture classification/segmentation. The proposed idea is to feed a Fully Convolutional Network with specific texture descriptors. These texture features are extracted from images by using an empirical curvelet transform. We propose a method to 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 deep learning networks. Our approach is finally evaluated on several datasets and compare the results to various state-of-the-art algorithms and show that the proposed method dramatically outperform all existing ones.