Fingerprint indexing with pose constraint

作者：

Highlights：

• We proposed a learning-based fingerprint pose estimation algorithm, which is used to coarsely align fingerprints.

• We proposed an improved Locality Sensitive Hashing algorithm for minutiae descriptor.

• Both fingerprint indexing accuracy and speed are significantly improved with the proposed algorithm.

摘要

Highlights•We proposed a learning-based fingerprint pose estimation algorithm, which is used to coarsely align fingerprints.•We proposed an improved Locality Sensitive Hashing algorithm for minutiae descriptor.•Both fingerprint indexing accuracy and speed are significantly improved with the proposed algorithm.

论文关键词：Fingerprint indexing,Pose estimation,Locality Sensitive Hashing

论文评审过程：Received 22 August 2015, Revised 2 December 2015, Accepted 3 January 2016, Available online 16 January 2016, Version of Record 27 February 2016.

论文官网地址：https://doi.org/10.1016/j.patcog.2016.01.006