Mask Attack Detection Using Vascular-weighted Motion-robust rPPG Signals

TL;DR

This paper introduces a novel, motion-robust rPPG-based method for detecting 3D mask attacks on face recognition systems, utilizing face stitching, blood vessel emphasis, and a lightweight neural network for improved accuracy.

Contribution

It proposes a new face alignment and encoding technique with a specialized neural network to enhance mask attack detection performance and generalization.

Findings

Significant improvement over state-of-the-art methods in intra- and cross-dataset tests.

Robust face alignment at pixel level enhances rPPG signal quality.

Weighted spatial-temporal representation improves mask attack detection accuracy.

Abstract

Detecting 3D mask attacks to a face recognition system is challenging. Although genuine faces and 3D face masks show significantly different remote photoplethysmography (rPPG) signals, rPPG-based face anti-spoofing methods often suffer from performance degradation due to unstable face alignment in the video sequence and weak rPPG signals. To enhance the rPPG signal in a motion-robust way, a landmark-anchored face stitching method is proposed to align the faces robustly and precisely at the pixel-wise level by using both SIFT keypoints and facial landmarks. To better encode the rPPG signal, a weighted spatial-temporal representation is proposed, which emphasizes the face regions with rich blood vessels. In addition, characteristics of rPPG signals in different color spaces are jointly utilized. To improve the generalization capability, a lightweight EfficientNet with a Gated Recurrent Unit (GRU) is designed to extract both spatial and temporal features from the rPPG spatial-temporal representation for classification. The proposed method is compared with the state-of-the-art methods on five benchmark datasets under both intra-dataset and cross-dataset evaluations. The proposed method shows a significant and consistent improvement in performance over other state-of-the-art rPPG-based methods for face spoofing detection.