Restrictive voting technique for faces spoofing attack

Mahmoud Omara; Mahmoud Fayez; H. Khaled; Said Ghoniemy

Author(s)

Mahmoud Omara Faculty of Computer and information sciences, Ain Shams University, Egypt

Mahmoud Fayez Faculty of Computer and information sciences, Ain Shams University, Egypt

H. Khaled Faculty of Computer and information sciences, Ain Shams University, Egypt

Said Ghoniemy Faculty of Computer and information sciences, Ain Shams University, Egypt

Abstract

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 biometric authentication systems that aim to prevent unauthorized access. This paper proposes a modified version of majority voting that combines the votes of six classifiers for multiple video chunks in order to enhance the accuracy of face anti-spoofing. The used approach involves sampling sub-videos of 2 seconds each with a one-second overlap and classifying each sub-video using multiple classifiers. Classifications for each sub-video across all classifiers are ensembled to decide the complete video classification. The main focus is on the False Acceptance Rate (FAR) metric to highlight the importance of preventing unauthorized access. The proposed method was assessed using the Replay Attack dataset [1] and yielded a FAR of zero. The Half Total Error Rate (HTER) and Equal Error Rate (EER) were also reported and gained a better result than most state-of-the-art methods. The experimental results demonstrate that the proposed method reduces the FAR to a significant extent, which is critical for real-world face anti-spoofing applications.

Publication Details

Page(s) 1-13

DOI DOI not available

Published Journal: International Journal of Communication Networks and Information Security, Volume: 15, Issue: 1, Year: 2023

Request the full text from PASTIC

Keywords

Majority voting, Machine-Learning, Face Anti-spoofing, Voting Techniques