We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
Monocular Facial Presentation–Attack–Detection: Classifying Near-Infrared Reflectance Patterns.
- Authors
Hassani, Ali; Diedrich, Jon; Malik, Hafiz
- Abstract
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.
- Subjects
MONOCULARS; HUMAN facial recognition software; REFLECTANCE; MANUFACTURING processes; MATHEMATICAL models; ALBEDO
- Publication
Applied Sciences (2076-3417), 2023, Vol 13, Issue 3, p1987
- ISSN
2076-3417
- Publication type
Article
- DOI
10.3390/app13031987