Saliency Region Detection via Graph Model and Statistical Learning

Saliency region detection plays an important role in computer vision aiming at discovering the salient objects in an image. This paper proposes a novel saliency detection algorithm (named as GMSL) via combining graph model and statistical learning. Firstly, the algorithm generates an initial saliency map by manifold ranking and optimizes it with absorbing Markov chain, both of which are based on graph model. Then, Bayes estimation with color statistical models is utilized as statistical learning to assign the saliency values to each pixel and further purify the map. Extensive experiments comparing with several state-of-the-art saliency detection works tested on different datasets demonstrate the superiority of the proposed algorithm.