Face anti-spoofing countermeasure: Efficient 2D materials classification using polarization imaging

Spoofing is an act to impersonate a valid user of any biometric systems in order to gain access. In a face biometric system, an imposter might use some fake masks that mimic the real user face. Existing countermeasures against spoofing adopt face texture analysis, motion detection and surface reflection analysis. For the purpose of face anti-spoofing analysis, skin structure is a key factor in achieving the target of our study. Skin consists of multiple layers structure which produces multiple reflections: surface and subsurface reflections. In this paper, we proposed a measure to discriminate between a genuine face and a printed paper photo based on physical properties of the materials which contribute to its distinctive reflection values. In order to differentiate the reflections, polarized light (light that vibrates in a single direction) can be used. The Stokes parameters are applied to generate the Stokes images which are then used to produce the final image known as Stokes degree of linear polarization (SDOLP) image. The intensity of the SDOLP image is investigated statistically which has shown promising results in the materials classification, between the skin and the paper mask. Furthermore, comparison between the experimental results from two skin color groups, black and others show that the SDOLP data distribution of black skin is similar to the printed paper photo of the same skin group.