Multi-scale salient object detection using graph ranking and global–local saliency refinement

作者：

Highlights：

• Salient object detection using multi-layered graph ranking.

• Local-global saliency refinement using objectness-measure and random forests.

• Region and boundary information for salient object detection.

• Feature relevance for object/background discrimination.

摘要

Highlights•Salient object detection using multi-layered graph ranking.•Local-global saliency refinement using objectness-measure and random forests.•Region and boundary information for salient object detection.•Feature relevance for object/background discrimination.

论文关键词：Salient object detection (SOD),Multi-layer graphs,Random forests,Region and boundary information,Feature relevance

论文评审过程：Received 15 January 2016, Revised 28 July 2016, Accepted 28 July 2016, Available online 5 August 2016, Version of Record 18 August 2016.

论文官网地址：https://doi.org/10.1016/j.image.2016.07.007