A Robust Face Recognition Method Based on AdaBoost, EHMM and Sample Perturbation

Face recognition is a classical topic in pattern classification, although there are already some good methods and applications, robust face recognition methods are always pursued. In this paper, based on AdaBoost, embedded hidden Markov model(EHMM), and sample perturbation, a novel and robust face recognition method is proposed. Experiments results show that the proposed method can get higher recognition rate on benchmark datasets. Furthermore, the proposed method show robustness on the test samples with different illumination and shelter.