Pose-invariant face recognition with homography-based normalization

作者：

Highlights：

• We propose a highly efficient and accurate pose normalization approach for pose-invariant face recognition.

• This is the first time that homography is utilized for face synthesis.

• The proposed approach covers the full range of pose variations within ±90° of yaw.

• The proposed approach outperforms existing methods on four popular face databases.

摘要

Highlights•We propose a highly efficient and accurate pose normalization approach for pose-invariant face recognition.•This is the first time that homography is utilized for face synthesis.•The proposed approach covers the full range of pose variations within ±90° of yaw.•The proposed approach outperforms existing methods on four popular face databases.

论文关键词：Pose-invariant face recognition,Face synthesis,Pose normalization,Homography

论文评审过程：Received 15 July 2016, Revised 1 November 2016, Accepted 28 November 2016, Available online 29 November 2016, Version of Record 12 March 2017.

论文官网地址：https://doi.org/10.1016/j.patcog.2016.11.024