Face Anti-Spoofing Based on Multi-layer Domain Adaptation

Fengshun Zhou, Chenqiang Gao, Fang Chen, Chaoyu Li, Xindou Li, Feng Yang, Yue Zhao

Abstract: With the popularity of face recognition technology, people have put forward higher requirements for the security of face recognition system. Face anti-spoofing detection attracts extensive attention and many methods been proposed. However, these methods perform poorly in cross scenes. To solve this problem, we propose a face anti-spoofing detection algorithm based on domain adaptation. We apply Maximum Mean Discrepancy (MMD) to multi-layer network distribution adaptation, which improves the generalization ability of the model. To further improve the performance of face anti-spoofing detection, we fuse the low-level features with the high-level features of convolutional neural network for face anti-spoofing detection. Two widely used datasets are used to test the proposed method. The experimental results show that the proposed algorithm outperforms state-of-the-art approaches.