Large Scale Identity Deduplication Using Face Recognition Based on Facial Feature Points

The algorithm of 105 facial feature points localization has been proposed in [1]. In this paper, we studied the stability of these feature points in different photos of the same person, and then we presented an improved face recognition system using these facial feature points to perform face recognition and check duplicate entries in database. All of these analyses and experiments are performed on identity photographs. Experimental results show that our recognition algorithm has obvious improvement in normal face recognition application and also performances satisfactorily in finding out duplicate entries in huge face image database of more than 60,000 items.