Salient region detection based on the superpixel and texture
Jichun Li, Encai Zhang, Haotian Yu, Haihong Lin, Guannan Chen · 2017
Salient region detection has become one of the hot research topics in pattern recognition in recent years. In this paper, an effective SLIC superpixel-based and global texture contrast salient region detection algorithm is proposed. SLIC algorithm is used to extract the initial superpixels in the image preprocessing stage, and then combined with the textural features of each superpixel to calculate global contrast differences and spatial coherence. Finally, the key areas are enhanced and detected. Experimental results in the public database have been shown that the method performs better than the others in precision, recall and F-measure.