Research on Face Recognition Based on PCA and FLD

Abstract

Aiming at the complex background, illumination change, attitude expression and occlusion problems encountered in face recognition, this paper uses PCA algorithm to obtain the feature space of the training sample set, and FLD algorithm to obtain the fusion feature space, and then trains and recognizes the projected face in the feature space. The experimental results show that the algorithm of face recognition based on improved PCA + FLD recognition rate is higher than the traditional face recognition algorithm that is faster, a right blend of the two algorithms, the advantages of human face recognition rate increased, but there are also some face is to identify the subject is not successful, because the distance of testing and training pictures don’t match.