Face liveness detection based on enhanced local binary patterns

For face recognition systems, impostors can obtain legal identity authentication by presenting the printed images, the downloaded images or candid videos to the sensor. In this paper, an enhanced face local binary feature (ELBP) of a face map is extracted as a classification feature to identify whether the face map is a real face or a fake face. Compared with the dynamic or static methods proposed in the previous literature, the proposed method is convenient and effective. We achieved over 95% correct recognition rate on NUAA datasets. Through comprehensive analysis and comparison with other static-based algorithms such as M-LBP or LTP, the proposed algorithm can achieve better performances.