An Improved Algorithm for Saliency Object Detection Based on Manifold Ranking

Abstract

The goal of saliency detection is to locate important pixels or regions in an image. To overcome the shortage that the spatial connectivity of every region is modeled only via k-regular graph, and do not consider the deficiency between multi-layer super pixel segmentations based on manifold ranking, an improved method is proposed. First, we tackle an image from a scale point of view and use a multi-layer approach to analyze saliency cues. Second, through building a graph model which is on the basis of k- regular graph, we connect the nodes belonging to the same cluster and located in the same spatial connected area with edges, to highlight the whole goal more uniformly and evenly, then used manifold ranking to generate multi-layer saliency map. Finally, the final saliency map is got through weighted linear fusion. By the experimental comparison of the 3 quantitative evaluation indexes of 8 start-of-the-art methods on three datasets, our method proves the effectiveness and superiority.