Abstract
Face anti-spoofing (FAS) is to protect facial recognition systems against presentation attacks. However, recent research on FAS often neglects real-world conditions, such as changing illumination, varying angles of face, and motion blur within a video. These conditions lead to inconsistent feature quality across face images, where low-quality features can cause the model to learn unreliable information during training. Moreover, frames with low feature quality within videos result in inaccurate decisions. To address this issue, we propose the Face Image Quality Assessment Based Face Anti-Spoofing System (FIQA-FAS), which integrates a face image quality assessment module with a face anti-spoofing module. FIQA-FAS assesses the feature quality extracted from each face image and uses the quality score to compute a weighted prediction for deciding if the face in a video is live or spoof. We demonstrate the effectiveness of FIQA-FAS through experiments on the SIW and SIW-M datasets. To further demonstrate our model’s capabilities, we introduce a novel simulated scenario that mimics the real world, where our model outperforms other SOTA.