Face presentation attack detection using guided scale texture

Abstract

Aiming to counter presentation attack (also known as spoofing attack) in face recognition system, a face presentation attack detection (also known as spoofing detection or liveness detection) scheme based on guided scale texture is proposed. In order to minimize the influence of the redundant noise contamination, guided scale space is proposed to reduce the redundancy of the original facial texture and to extract more powerful facial edges. Based on the guided scale space, two guided scale texture descriptors are proposed to extract liveness detection features, and they are guided scale based local binary pattern (GS-LBP) and local guided binary pattern (LGBP). GS-LBP takes advantage of the edge-preserving property of the guided scale space, and joint quantization is used in LGBP to encode the neighboring relationships of the original face and the guided scale face without using additional features. With the guided scale texture features, presentation attack detection is accomplished by the use of a linear support vector machine classifier. Experiments are done with public MSU MFSD, CASIA FASD, Replay-Attack and Replay-Mobile databases, and the results indicate its effectiveness. The proposed method can effectively be applied for countering photo attack and video attack in face recognition systems.