Sparse 3D directional vertices vs continuous 3D curves: Efficient 3D surface matching and its application for single model face recognition

作者：

Highlights：

• A 3D directional vertices (3D2V) approach is proposed to efficiently represent and match 3D surfaces.

• It can significantly reduce the data storage requirement and computation time of 3D matching algorithms.

• A moderate increase of recognition accuracy is also observed.

• It provides a new tool that can be used for developing fast 3D surface matching algorithms for large scale 3D data classification and retrieval.

摘要

•A 3D directional vertices (3D2V) approach is proposed to efficiently represent and match 3D surfaces.•It can significantly reduce the data storage requirement and computation time of 3D matching algorithms.•A moderate increase of recognition accuracy is also observed.•It provides a new tool that can be used for developing fast 3D surface matching algorithms for large scale 3D data classification and retrieval.

论文关键词：3D surface matching,3D directional vertex,Fast 3D matching,Storage space,3D face recognition,3D curve,Hausdorff distance,Iterative closest points

论文评审过程：Received 1 June 2016, Revised 11 December 2016, Accepted 12 December 2016, Available online 14 December 2016, Version of Record 17 January 2017.

论文官网地址：https://doi.org/10.1016/j.patcog.2016.12.009