Fine-structured object segmentation via neighborhood propagation
作者：
Highlights：
• We propose a method for fine-structured object segmentation via label propagation.
• A novel affinity graph combining local and nonlocal connections is constructed.
• We incorporate appearance models as labeling preference for the label propagation.
• The energy minimization is achieved with a globally optimal closed-form solution.
• Extensive experimental results demonstrate the effectiveness of our method.
摘要
Highlights•We propose a method for fine-structured object segmentation via label propagation.•A novel affinity graph combining local and nonlocal connections is constructed.•We incorporate appearance models as labeling preference for the label propagation.•The energy minimization is achieved with a globally optimal closed-form solution.•Extensive experimental results demonstrate the effectiveness of our method.
论文关键词：Fine-structured object segmentation,Label propagation,Affinity graph,Local and nonlocal neighborhood,Region cost
论文评审过程：Received 26 January 2016, Revised 11 April 2016, Accepted 21 May 2016, Available online 24 May 2016, Version of Record 2 June 2016.
论文官网地址：https://doi.org/10.1016/j.patcog.2016.05.025
