Illumination and pose variable face recognition via adaptively weighted ULBP_MHOG and WSRC

作者：

Highlights：

•

• WULBP_MHOG is extracted as the robust feature and fused with Tan’s method.

• MHOG has lower dimension than original HOG and includes multiple information.

• Information entropy is used to calculate weights of blocks, which is adaptive.

• Weighted sparse representation (WSRC) is as the classifier to test face images.

摘要

•WULBP_MHOG is extracted as the robust feature and fused with Tan’s method.•MHOG has lower dimension than original HOG and includes multiple information.•Information entropy is used to calculate weights of blocks, which is adaptive.•Weighted sparse representation (WSRC) is as the classifier to test face images.

论文关键词：Illumination and pose changes,Adaptive weights,ULBP_MHOG,WSRC,Face recognition

论文评审过程：Received 20 January 2017, Revised 29 April 2017, Accepted 28 July 2017, Available online 7 August 2017, Version of Record 18 August 2017.

论文官网地址：https://doi.org/10.1016/j.image.2017.07.008