Multi-scale edge detection and image segmentation

Abstract

In this paper, we propose a novel multi-scale edge detection and vector field design scheme. We show that using multiscale techniques edge detection and segmentation quality on natural images can be improved significantly. Our approach eliminates the need for explicit scale selection and edge tracking. Our method favors edges that exist at a wide range of scales and localize these edges at finer scales. This work is then extended to multi-scale image segmentation using our anisotropic diffusion scheme.