Learn Convolutional Neural Network for Face Anti-Spoofing
This addresses the problem of improving security in face recognition systems against spoofing attacks, representing an incremental advance by applying CNNs to a known bottleneck.
The paper tackled face anti-spoofing by using a deep convolutional neural network (CNN) to learn discriminative features instead of hand-crafted ones, achieving over 70% relative decrease in Half Total Error Rate (HTER) on two challenging datasets compared to state-of-the-art methods.
Though having achieved some progresses, the hand-crafted texture features, e.g., LBP [23], LBP-TOP [11] are still unable to capture the most discriminative cues between genuine and fake faces. In this paper, instead of designing feature by ourselves, we rely on the deep convolutional neural network (CNN) to learn features of high discriminative ability in a supervised manner. Combined with some data pre-processing, the face anti-spoofing performance improves drastically. In the experiments, over 70% relative decrease of Half Total Error Rate (HTER) is achieved on two challenging datasets, CASIA [36] and REPLAY-ATTACK [7] compared with the state-of-the-art. Meanwhile, the experimental results from inter-tests between two datasets indicates CNN can obtain features with better generalization ability. Moreover, the nets trained using combined data from two datasets have less biases between two datasets.