A NEW ENSEMBLE OF TEXTURE DESCRIPTORS BASED ON LOCAL APPEARANCE-BASED METHODS FOR FACE ANTI-SPOOFING SYSTEM
H Vinutha, G. Thippeswamy · 2022
Face is a very popular non-intrusive modality used in biometrics recognition. Spoofing attack is a method using which an illegitimate access is made via the face biometric system. Face anti-spoofing technique we implemented using static approaches are based on descriptors that are extracted using Local appearance-based methods for the face images of NUAA Photo Impostor database. This paper discusses few variations in the input image that is used for print attacks that can be explored while designing the features. An ensemble of local texture features are extracted upon which a kNN classifier applied to determine real and impostor face images. Our objective is to lay down the effectiveness of different type of descriptors extracted for Face Anti-spoofing technique to detect print attacks.