Local histogram specification for face recognition under varying lighting conditions

作者：

Highlights：

• We improve the TT preprocessing method using local histogram specification.

• Our methods can remove both the low and high frequency illuminations on face images.

• Our methods can enhance face features lying in the low frequency part of face images.

• We report the recognition rate of 81.6% on the CAS-PEAL-R1 database.

摘要

•We improve the TT preprocessing method using local histogram specification.•Our methods can remove both the low and high frequency illuminations on face images.•Our methods can enhance face features lying in the low frequency part of face images.•We report the recognition rate of 81.6% on the CAS-PEAL-R1 database.

论文关键词：Local histogram specification,Local histogram statistics,Face recognition,High frequency illumination,Low frequency face features

论文评审过程：Received 12 July 2013, Revised 7 December 2013, Accepted 21 February 2014, Available online 5 March 2014.

论文官网地址：https://doi.org/10.1016/j.imavis.2014.02.010