Multi-stream Face Anti-spoofing System Using 3D Information.

Face anti-spoofing plays a crucial role in face recog-nition systems widely used in smart devices and security systems. In this paper, we propose a multi-stream fusion system based on a 3D camera by making full use of 3D information for face anti-spoofing. This 3D information is composed of depth maps and Surface Normal Maps (SNM). Detailed discussions about systems are given. Comparison among different modalities and comparison among other methods are provided through several experiments on the public WMCA dataset and our self-build Anti-3D dataset. Due to fewer parameters and less time overhead, we also implement the system on hardware platforms with a 3D camera.