A novel saliency detection method via manifold ranking and compactness prior

Abstract

For improving the performance of saliency detection, several algorithms used graph construction have achieved excellent results. This paper proposes a novel bottom-up approach of saliency detection, which takes the advantages of both prior background and compactness. At first, we optimize the image boundary selections, by removing erroneous sections with a fixed threshold, to achieve more accurate saliency estimation results. The saliency map obtained by ranking with background queries can be optimized with compactness prior. The objects of salient are connected regions which are group together, with a compact form which are spatial distributed. Compared to the 8 state-of-the-art saliency detection approaches, our experimental results which test on the three public datasets show that the proposed algorithm improves accuracy and robustness significantly. This algorithm can find its potential applications in many different areas, but it is best suit for medical science and technologies because of high accuracy requirements. It can be used in the medical imaging processing to accurately differentiate tumor from bones, muscles and fats.