Fast Marching Based Superpixels Generation

Abstract

In this article, we present a fast-marching based algorithm for generating superpixel (FMS) partitions of images. The idea behind the algorithm is to draw an analogy between waves propagating in an heterogeneous medium and regions growing on an image at a rate depending on the local color and texture. The FMS algorithm is evaluated on the Berkeley Segmentation Dataset 500. It yields results in term of boundary adherence that are comparable to the ones obtained with state of the art algorithms including SLIC or ERGC, while improving on these algorithms in terms of compactness and density.