Abstract: To obtain a more refined and accurate result of a salient detection object,in this paper we proposed a novel salient object detection algorithm which takes both background and foreground cues into consideration,and this algorithm integrates a bottom-up coarse salient regions extraction and a top-down background weight map measure into a unified optimization framework.Where in the coarse saliency map is fused by three prior components,the first is local contrast map which is more accordance with the biopsychology law,the second is frequency prior map,and the third is the color distributed prior map.During the computation of the background weight map,we first construct an undirected graph based on superpixel segmentation and select nodes on the border as an initial query to represent the background,then we perform a relevance propagation to generate the background weight map.Comprehensive comparisons with 10 state-of-the-art solutions on two benchmark datasets-MSRA1000 and ECSSD indicate that our algorithm with a superior performance.