A novel graph-based optimization framework for salient object detection

作者：

Highlights：

• A novel graph-based optimization framework for salient object detection is proposed in the paper.

• Multiple graphs are employed in our optimization framework to better describe a natural scene image.

• Visual rarity is modeled as a regularization term in our framework to better detect saliency.

• Experimental results on four datasets with fifteen methods prove the effectiveness of our method.

摘要

Highlights•A novel graph-based optimization framework for salient object detection is proposed in the paper.•Multiple graphs are employed in our optimization framework to better describe a natural scene image.•Visual rarity is modeled as a regularization term in our framework to better detect saliency.•Experimental results on four datasets with fifteen methods prove the effectiveness of our method.

论文关键词：Optimization framework,Multiple graphs,Visual rarity,Saliency detection

论文评审过程：Received 26 July 2016, Revised 14 September 2016, Accepted 19 October 2016, Available online 22 October 2016, Version of Record 5 November 2016.

论文官网地址：https://doi.org/10.1016/j.patcog.2016.10.025