Scale space clustering evolution for salient region detection on 3D deformable shapes
作者：
Highlights：
• A salient region detection method on 3D deformable shapes is proposed.
• The method relies on clustering of a data set derived from the scale space of the auto diffusion function parameterized by t.
• There exists an evolution of the scalar field across time scales, and that all the salient regions on 3D shapes are exposed during this process.
摘要
•A salient region detection method on 3D deformable shapes is proposed.•The method relies on clustering of a data set derived from the scale space of the auto diffusion function parameterized by t.•There exists an evolution of the scalar field across time scales, and that all the salient regions on 3D shapes are exposed during this process.
论文关键词：Deformable shape segmentation,Salient region detection,Diffusion geometry,Clustering algorithm,Persistent homology
论文评审过程：Received 31 January 2017, Revised 5 May 2017, Accepted 20 May 2017, Available online 22 May 2017, Version of Record 12 July 2017.
论文官网地址：https://doi.org/10.1016/j.patcog.2017.05.018
