Multi-layer graph constraints for interactive image segmentation via game theory

作者：

Highlights：

• Multi-layer graph constraints are utilized for the interactive image segmentation.

• Labeling information is introduced into the conventional pixel–superpixel combinational model.

• The optimization based on game theory is proposed for the combinational energy functions.

• The proposed method can obtain better performance than the state-of-the-art methods.

摘要

•Multi-layer graph constraints are utilized for the interactive image segmentation.•Labeling information is introduced into the conventional pixel–superpixel combinational model.•The optimization based on game theory is proposed for the combinational energy functions.•The proposed method can obtain better performance than the state-of-the-art methods.

论文关键词：Image segmentation,Superpixel,Multi-layer graph,Nonparametric learning,Game theory

论文评审过程：Received 19 September 2015, Revised 14 January 2016, Accepted 18 January 2016, Available online 26 January 2016, Version of Record 21 March 2016.

论文官网地址：https://doi.org/10.1016/j.patcog.2016.01.018