Template adaptation for face verification and identification

作者：

Highlights：

• Face recognition can be improved by combining linear classifiers with deep features.

• This simple strategy outperforms the state-of-the-art by a wide margin.

• We justify this conclusion by studying a variety of hyperparameters on performance.

摘要

•Face recognition can be improved by combining linear classifiers with deep features.•This simple strategy outperforms the state-of-the-art by a wide margin.•We justify this conclusion by studying a variety of hyperparameters on performance.

论文关键词：Face recognition,Biometrics,Face verification

论文评审过程：Received 13 October 2017, Revised 18 April 2018, Accepted 12 September 2018, Available online 21 September 2018, Version of Record 3 October 2018.

论文官网地址：https://doi.org/10.1016/j.imavis.2018.09.002