Open-set face identification with index-of-max hashing by learning

作者：

Highlights：

• A systematic study on face identification problem in both open and close-set evaluation protocols.

• A supervised learning-based Index-of-Maximum hashing for deep facial feature protection and compression is outlined.

• Several feature level and score level fusion strategies for face identification problem are explored.

• Three large unconstraint face datasets of increasing complexity: LFW dataset, VGG2 and the IJB-C dataset are used for evaluation.

摘要

•A systematic study on face identification problem in both open and close-set evaluation protocols.•A supervised learning-based Index-of-Maximum hashing for deep facial feature protection and compression is outlined.•Several feature level and score level fusion strategies for face identification problem are explored.•Three large unconstraint face datasets of increasing complexity: LFW dataset, VGG2 and the IJB-C dataset are used for evaluation.

论文关键词：Secure open-set face identification,Index-of-max hashing,Fusion,Privacy

论文评审过程：Received 18 February 2019, Revised 20 December 2019, Accepted 12 February 2020, Available online 14 February 2020, Version of Record 11 March 2020.

论文官网地址：https://doi.org/10.1016/j.patcog.2020.107277