Conditional Random Field based salient proposal set generation and its application in content aware seam carving
作者：
Highlights：
• Effective salient object proposal generation using conditional random fields is proposed.
• Bayesian inference framework for edge saliency map computation is formulated.
• Content aware seam carving is done using the SalProp proposals.
• Objectness score of candidate windows ranked by saliency score.
• Exhaustive comparative analysis on proposed object proposal generation and seam carving with IRQA metrics on competing methods.
摘要
•Effective salient object proposal generation using conditional random fields is proposed.•Bayesian inference framework for edge saliency map computation is formulated.•Content aware seam carving is done using the SalProp proposals.•Objectness score of candidate windows ranked by saliency score.•Exhaustive comparative analysis on proposed object proposal generation and seam carving with IRQA metrics on competing methods.
论文关键词：Structured prediction,Edge classification,Salient edge density based scoring,Bayesian probabilistic edge map,Salient region preserving seam carving
论文评审过程：Received 27 April 2019, Revised 28 February 2020, Accepted 21 May 2020, Available online 27 May 2020, Version of Record 5 June 2020.
论文官网地址：https://doi.org/10.1016/j.image.2020.115890
