Gabor Binary Codes for Face Recognition

There are many challenges in face recognition task, such as illumination, facial expression and accessory etc. in this paper, an novel method, called Gabor Binary Code (GBC) is introduced to extract robustness features for face recognition against these disturbance. At first, the original gray images was convoluted with a series of Gabor Wavelet jets and got the corresponding Gabor Magnitude Pictures (GMP), then the GBC will be constructed by these GMP under the basic idea of Local Binary Pattern (LBP). Because of containing both the information of local texture and block gray varying, GBC features are overwhelming comparing with Local Binary Patterns(LBP), Gavor Wavelet and Independent Component Analysis(ICA) methods. Series of experimental results show that it has improve the recognition rate greatly even in bad condition.