A novel multi-graph framework for salient object detection

• Published in: The Visual computer 2019-11, Vol.35 (11), p.1683-1699
• Main Authors: Lu, Ye, Zhou, Kedong, Wu, Xiyin, Gong, Penghan
• Format: Article
• Language: English
• Subjects: Artificial Intelligence; Computer Graphics; Computer Science; Deep learning; Graphical representations; Image Processing and Computer Vision; Image retrieval; Methods; Object recognition; Original Article; Propagation; Salience; Seeds; Semantics
• ISSN: 0178-2789; 1432-2315
• DOI: 10.1007/s00371-019-01637-2

Graph-based methods have been widely adopted for predicting the most attractive region in an image. Most of the existing graph-based methods only utilize single graph to describe the image information, and thus cannot adapt for complex scenes. In this paper, a novel multi-graph framework for salient object detection is proposed. The proposed method is divided into three steps. Firstly, an image is divided into superpixels and described as a multi-graph, where superpixels are represented as nodes and their information is computed by color space and location space. Secondly, the multiple graphs are combined into a novel multi-graph-based manifold ranking propagation framework to obtain a coarse map. Finally, a map refinement model is developed to improve the quality of the coarse map. Experimental results on four challenging datasets show that the proposed method performs favorably against the state-of-the-art salient object detection methods.