Fast two-stage segmentation via non-local active contours in multiscale texture feature space

Abstract

In this paper, a new non-local active contour model is proposed for fast unsupervised segmentation of texture images. Under our framework, problems of texture description are addressed in a texture feature space. Then, the texture features are adaptively represented across scales and their homogeneities are efficiently measured by Wasserstein metric. With total variation regularization, an external energy including a non-local term and a global term is introduced into our energy functional, which can integrate non-local patch interactions with region homogeneities inside or outside the evolving contours. Our model proportionally reaches the balance between local and global homogeneities of features and exactly extracts meaningful objects. Finally, the segmentation approach is split into two stages, coarse segmentation for fast location in the coarse-scale space and accurate segmentation for bias correction in the fine-scale space. And the two segmentation problems are reformulated into the convex optimization framework, providing a global minimizer to our active contour model. Segmentation results of the synthetic and real-world images show that our model can accurately segment object regions in a fast way.