Interactive image segmentation using label propagation through complex networks
作者：
Highlights：
• This paper presents a new graph-based interactive image segmentation method.
• It uses small-world complex networks to propagate the labels quickly.
• “Scribbles” loosely traced over the objects of interest may be used as seeds.
• The proposed method has low computational time and storage complexity.
• Its accuracy and speed are comparable to those of state-of-the-art methods.
摘要
•This paper presents a new graph-based interactive image segmentation method.•It uses small-world complex networks to propagate the labels quickly.•“Scribbles” loosely traced over the objects of interest may be used as seeds.•The proposed method has low computational time and storage complexity.•Its accuracy and speed are comparable to those of state-of-the-art methods.
论文关键词：Interactive image segmentation,Label propagation,Complex networks
论文评审过程：Received 14 June 2018, Revised 8 January 2019, Accepted 9 January 2019, Available online 9 January 2019, Version of Record 11 January 2019.
论文官网地址：https://doi.org/10.1016/j.eswa.2019.01.031
