An efficient multimodal face recognition method robust to pose variation

In the recent years, face recognition has obtained much attention. Using combined 2D and 3D face recognition is an alternative method to deal with face recognition. A novel multimodal face recognition algorithm based on Gabor wavelet information is presented in this paper. The Principal Component Analysis (PCA) and the Linear Discriminant analysis (LDA) have been used for size reduction. The system has combined 2D and 3D systems in the decision level which presents higher performance in contrast with methods which use only 2D and 3D systems, separately. The proposed algorithm is examined with FRAV3D database that has faces with pose variation and 95% performance that is achieved in rank-one for fusion experiment.