A prior-based graph for salient object detection
Jinxia Zhang, Krista A. Ehinger, Jundi Ding, Jingyu Yang · 2014
Recently, various graph-based methods have be proposed for salient object detection. These algorithms represent image points and their similarity as nodes and edges in a graph. Although the edge structure and weighting are the heart of these methods, the graph construction has not been studied in detail. In this paper, we exploit image priors, including spatial priors, color priors, and a central bias prior, to construct the graph. We connect nodes which are spatially close in the image, nodes which have similar color features, and the boundary nodes along the borders of the image, while weighting edges according to both their color similarity and spatial proximity. Moreover, we propose a new sine spatial distance instead of the commonly-used Euclidean spatial distance, which better captures the central bias in scenes. Extensive experiments show that our method outperforms thirteen state-of-the-art methods on four different image databases.