Monocular Facial Presentation-Attack-Detection: Classifying Near-Infrared Reflectance Patterns

Featured Application Face-recognition for monocular systems (e.g., phones and buildings). This paper presents a novel material spectroscopy approach to facial presentation-attack-defense (PAD). Best-in-class PAD methods typically detect artifacts in the 3D space. This paper proposes similar features can be achieved in a monocular, single-frame approach by using controlled light. A mathematical model is produced to show how live faces and their spoof counterparts have unique reflectance patterns due to geometry and albedo. A rigorous dataset is collected to evaluate this proposal: 30 diverse adults and their spoofs (paper-mask, display-replay, spandex-mask and COVID mask) under varied pose, position, and lighting for 80,000 unique frames. A panel of 13 texture classifiers are then benchmarked to verify the hypothesis. The experimental results are excellent. The material spectroscopy process enables a conventional MobileNetV3 network to achieve 0.8% average-classification-error rate, outperforming the selected state-of-the-art algorithms. This demonstrates the proposed imaging methodology generates extremely robust features.

Automated summary

This paper presents a novel facial imaging method for monocular systems, such as phones and buildings. By using controlled light and a mathematical model, it demonstrates the unique reflectance patterns of live and spoof faces. The proposed methodology is evaluated on a rigorous dataset and achieves excellent experimental results, outperforming state-of-the-art algorithms.