Local feature approach to dorsal hand vein recognition by Centroid-based Circular Key-point Grid and fine-grained matching

作者：

Highlights：

• We present novel and efficient method for dorsal hand vein recognition.

• We propose the Centroid-based Circular Key-point Grid for key-point generation.

• We introduce the MtSRC based fine-grained key-point matching.

• The performance of the local feature matching framework is largely improved.

• State of the art results are achieved on the NCUT Part A and Part B databases.

摘要

•We present novel and efficient method for dorsal hand vein recognition.•We propose the Centroid-based Circular Key-point Grid for key-point generation.•We introduce the MtSRC based fine-grained key-point matching.•The performance of the local feature matching framework is largely improved.•State of the art results are achieved on the NCUT Part A and Part B databases.

论文关键词：Hand vein recognition,Local feature matching,Centroid-based Circular Key-point Grid (CCKG),Multi-task Sparse Representation Classifier (MtSRC)

论文评审过程：Received 7 October 2015, Revised 5 June 2016, Accepted 12 July 2016, Available online 25 July 2016, Version of Record 20 February 2017.

论文官网地址：https://doi.org/10.1016/j.imavis.2016.07.001