MCCH: A novel convex hull prior based solution for saliency detection

Abstract Salient object detection has received much attention in the past decades. One of the representative approaches is utilizing the convex hull prior to find the salient object in the image. Recently, researchers have proposed many variant methods, which are based the convex hull prior. Nevertheless, most of them used a single center to construct the convex hull prior (CHP) map, while few attention has been made on the use of multiple centers. In this paper, we propose a multi-center convex hull prior based solution for salient object detection. To strengthen our solution, we also integrate two non-trivial optimizations: the first one is used to obtain an enhanced global color distinction prior (GCDP) map, and the second one is used to refine the preliminary saliency map. We conduct extensive experiments based on several widely used benchmarking datasets. The experimental results demonstrate that our solution is effective and competitive, compared against state-of-the-art saliency detection algorithms.