Multi-Frames Temporal Abnormal Clues Learning Method for Face Anti-Spoofing
This addresses security vulnerabilities in face recognition systems against spoofing attacks, with incremental improvements in efficiency and deployment.
The paper tackles face anti-spoofing by proposing EulerNet, a temporal feature fusion network that extracts abnormal clues from video frames, and introduces a lightweight labeling method and a new dataset of 30,000 samples. Experiments on OULU-NPU show the algorithm outperforms state-of-the-art methods and is deployed in systems serving millions of users.
Face anti-spoofing researches are widely used in face recognition and has received more attention from industry and academics. In this paper, we propose the EulerNet, a new temporal feature fusion network in which the differential filter and residual pyramid are used to extract and amplify abnormal clues from continuous frames, respectively. A lightweight sample labeling method based on face landmarks is designed to label large-scale samples at a lower cost and has better results than other methods such as 3D camera. Finally, we collect 30,000 live and spoofing samples using various mobile ends to create a dataset that replicates various forms of attacks in a real-world setting. Extensive experiments on public OULU-NPU show that our algorithm is superior to the state of art and our solution has already been deployed in real-world systems servicing millions of users.