Combining Neural Networks and Global Gabor Features in a Hybrid Face Recognition System

Abstract

Face recognition is the preferred mode of identification by humans: it is natural, robust and non-intrusive. Face recognition is the most effective and natural technique to identify a person, since it is the same as the way human does and there is no need to use any special equipment. In this paper, a novel face recognition approach is proposed based on Global Facial Features and Neural Networks. The Global Facial Features are extracted using a Gabor wavelet filter; by applying it on the whole image. The face registration is done with the help of Neural Networks and the classification with a nearest-neighbor classifier. The hybrid algorithm was tested on multiple face databases, ORL, Caltech, Yale and Yale B, in order to validate the face recognition rate. The results show that the new face recognition algorithm out-performs the conventional methods such as global Gabor face recognition with PCA in term of recognition rate.