Face Spoofing Detection Based on Improved Local Graph Structure

Abstract

Face spoofing attack is one of the recent security problems that face recognition systems are proven to be vulnerable to. The spoofing occurs when an attacker bypass the authentication scheme by presenting a copy of the face image for a valid user. Therefore, it's very easy to perform a face recognition spoofing attack with compare to other biometrics. This paper, presents a novel and efficient facial image representation for face spoofing called improved local graph structure (ILGS). We divide the input facial image into several regions and then we calculate local graph structure (LGS) codes for each region. On the other hand, the histograms are concatenated into an enhanced feature vector to detect spoofed facial image. Finally, performance of the proposed method is evaluated on the NUAA database.