ANALYSIS OF TEXTURAL FEATURES FOR FACE BIOMETRIC ANTI-SPOOFING

True authentication predicted on biometrics has received upsurge attention during the last few years, as it provides facile way to access the system through basic physical and behavioral characteristics. Face recognition being a non-intrusive recognition requires less participation from the user compared to iris, speech and fingerprint based biometric. Resistance to false authentication from photographs and video playbacks is a vigorous issue for successful biometric system. This paper analyzes different textural features and proposes a novel approach for anti-spoofing solution. Experiments were conducted on a publicly available face spoofing database REPLAY-ATTACK to validate textural analysis over a database containing printed photographs, photos and videos displayed on electronic screens. Results show that the approach is superior to the other existing state of art approaches tested on same database.