Convolutional Neural Networks for Face Anti- Spoofing and Liveness Detection

In past few decades, the development of the biometric identification techniques, such as fingerprint, iris, finger vein, and so on, has become quite mature and related applications have become very popular. The advance of GPU acceleration techniques and the impact of deep neural networks increase not only the accuracy, but also the popularity of face recognition systems. Although face recognition systems alleviate the problem of person identification, their applications would reveal a new challenging task, that is face spoofing and presentation attacks. No matter in a form of photos, videos, or 3D masks, face spoofing attacks can not only restrict the application of a face recognition system, but also increase its vulnerability in regard of security issues. Consequently, in this paper, a deep neural network scheme for face anti-spoofing and liveness detection is proposed to prevent the existing face recognition systems from common face spoofing attacks. The experimental results have demonstrated the robustness of the proposed method against print, cut, and replay attacks.