Complex networks driven salient region detection based on superpixel segmentation
作者：
Highlights：
• We propose an efficient method for salient region detection.
• An image is decomposed using superpixel segmentation.
• Similarity between the regions is calculated based upon the generated superpixels.
• Contrast, distribution and complex networks based saliency maps are generated.
• The proposed method has been compared with some state-of-the-art methods.
摘要
•We propose an efficient method for salient region detection.•An image is decomposed using superpixel segmentation.•Similarity between the regions is calculated based upon the generated superpixels.•Contrast, distribution and complex networks based saliency maps are generated.•The proposed method has been compared with some state-of-the-art methods.
论文关键词：Superpixel,Segmentation,Salient region detection,Saliency map,Complex networks
论文评审过程：Received 24 November 2015, Revised 4 September 2016, Accepted 7 January 2017, Available online 8 January 2017, Version of Record 12 March 2017.
论文官网地址：https://doi.org/10.1016/j.patcog.2017.01.010
