Isocentric color saliency in images

Abstract

In this paper we propose a novel computational method to infer visual saliency in images. The computational method is based on the idea that salient objects should have local characteristics that are different than the rest of the scene, being edges, color or shape, and that these characteristics can be combined to infer global information. The proposed approach is fast, does not require any learning and the experimentation shows that it can enhance interesting objects in images, improving the state of the art performance on a public dataset.