Robust heterogeneous discriminative analysis for face recognition with single sample per person

作者：

Highlights：

• A new patch-based method is proposed for single sample per person face recognition.

• A Fisher-like criterion is designed to extract discriminant information of patches.

• Two distance metrics are introduced simultaneously to enhance robustness.

• A fusion strategy called joint majority voting is developed for recognition.

摘要

•A new patch-based method is proposed for single sample per person face recognition.•A Fisher-like criterion is designed to extract discriminant information of patches.•Two distance metrics are introduced simultaneously to enhance robustness.•A fusion strategy called joint majority voting is developed for recognition.

论文关键词：Face recognition,Single sample per person,Heterogeneous representation,Fisher-like criterion,Joint majority voting

论文评审过程：Received 13 May 2018, Revised 16 October 2018, Accepted 4 January 2019, Available online 5 January 2019, Version of Record 30 January 2019.

论文官网地址：https://doi.org/10.1016/j.patcog.2019.01.005