Open-set Face Identification with Index-of-Max Hashing by Learning

•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.