Saliency detection based on extended boundary prior with foci of attention

In this paper, we propose a novel bottom-up paradigm for detecting visual saliency. Regarding the boundary as potential background (boundary prior), we firstly transfer the input color image into a graph with additional four virtual nodes. With a new type of edge called feature edge defined considering both color information and spatial distribution, geodesic saliency measure is used to obtain four saliency maps. Then a combination strategy of four maps is proposed, rendering a uniform saliency map to better suppress background and avoid over-suppression of salient object. Finally, we introduce a way of determining foci of attention based on maximal deviation from norm (MDN) to enhance the quality of saliency map. Experimental results on a benchmark dataset demonstrate the better performance of our proposed approach compared with several state-of-art methods.