Face Recognition Based On LBP And LNMF Algorithm

Nowadays, personal information tends to be electronic signature or digital password. How to accurately and efficiently identify an identity has become a hot area of research. Compared with the traditional method (such as password or card), face recognition based on biometrics has more advantages. But in some cases, it may result in a decline of the image due to light, posture and other reasons in the process of face recognition. In this paper, we propose a face recognition algorithm based on LBP and LNMF. A coefficient matrix can be obtained through the test sample database that have a projection to non-negative subspace. And according to a recent neighbor distance classification, we can achieve better results of pattern recognition ultimately. The result of the experiment show that the proposed method can effectively improve the recognition rate of the image.