An improved GrabCut on multiscale features

作者：

Highlights：

• GrabCut model combining optimized segmentation and feature selection is proposed.

• Feature extraction based on multiscale decomposition was also implemented.

• Significant improvement was observed in case of real images.

• Improvement was achieved without increasing user interaction.

摘要

•GrabCut model combining optimized segmentation and feature selection is proposed.•Feature extraction based on multiscale decomposition was also implemented.•Significant improvement was observed in case of real images.•Improvement was achieved without increasing user interaction.

论文关键词：Image segmentation,GrabCut,Multiscale feature,Total variation regularization,Inhomogeneity

论文评审过程：Received 27 March 2019, Revised 25 November 2019, Accepted 19 February 2020, Available online 22 February 2020, Version of Record 6 March 2020.

论文官网地址：https://doi.org/10.1016/j.patcog.2020.107292