Improving Face Anti-Spoofing by 3D Virtual Synthesis
This addresses the high cost of data collection for face recognition security systems, offering an incremental improvement through synthetic data generation.
The paper tackles the problem of acquiring expensive spoof data for face anti-spoofing by synthesizing virtual spoof data in 3D space, resulting in significantly boosted anti-spoofing performance when combined with a data balancing strategy.
Face anti-spoofing is crucial for the security of face recognition systems. Learning based methods especially deep learning based methods need large-scale training samples to reduce overfitting. However, acquiring spoof data is very expensive since the live faces should be re-printed and re-captured in many views. In this paper, we present a method to synthesize virtual spoof data in 3D space to alleviate this problem. Specifically, we consider a printed photo as a flat surface and mesh it into a 3D object, which is then randomly bent and rotated in 3D space. Afterward, the transformed 3D photo is rendered through perspective projection as a virtual sample. The synthetic virtual samples can significantly boost the anti-spoofing performance when combined with a proposed data balancing strategy. Our promising results open up new possibilities for advancing face anti-spoofing using cheap and large-scale synthetic data.