Masked fake face detection using radiance measurements
- 12 March 2009
- journal article
- Published by Optica Publishing Group in Journal of the Optical Society of America A
- Vol. 26 (4), 760-766
- https://doi.org/10.1364/josaa.26.000760
Abstract
This research presents a novel 2D feature space where real faces and masked fake faces can be effectively discriminated. We exploit the reflectance disparity based on albedo between real faces and fake materials. The feature vector used consists of radiance measurements of the forehead region under 850 and illuminations. Facial skin and mask material show linearly separable distributions in the feature space proposed. By simply applying Fisher’s linear discriminant, we have achieved 97.78% accuracy in fake face detection. Our method can be easily implemented in commercial face verification systems.
Keywords
This publication has 4 references indexed in Scilit:
- Reflection properties of nanostructure-arrayed silicon surfacesNanotechnology, 2000
- The evolution of human skin colorationJournal of Human Evolution, 2000
- Determining Generative Models of Objects Under Varying Illumination: Shape and Albedo from Multiple Images Using SVD and IntegrabilityInternational Journal of Computer Vision, 1999
- Photometric stereo under a light source with arbitrary motionJournal of the Optical Society of America A, 1994