Restrictive Voting Technique for Faces Spoofing Attack

Face anti-spoofing has become widely used due to the increasing use of biometric authentication systems that rely on facial recognition. It is a critical issue in aim prevent unauthorized access. In this paper, we propose modified version majority voting ensembles votes six classifiers for multiple video chunks improve accuracy face anti-spoofing. Our approach involves sampling sub-videos 2 seconds each with one-second overlap and classifying sub-video using classifiers. We then ensemble classifications across all decide complete classification. focus False Acceptance Rate (FAR) metric highlight importance preventing evaluated our method Replay Attack dataset achieved zero FAR. also reported Half Total Error (HTER) Equal (EER) gained better result than most state-of-the-art methods. experimental results show proposed significantly reduces FAR, which crucial real-world applications.