Discriminative representation combinations for accurate face spoofing detection. (January 2019)

• Record Type: Journal Article
• Authors: Song, Xiao; Zhao, Xu; Fang, Liangji; Lin, Tianwei
• Is Part Of: Pattern recognition. Volume 85(2019:Jan.)
• Page Start: 220
• Page End: 231
• Publication Date: 2019-01
• Subjects: Face presentation attack detection -- Template face registration -- Binocular depth -- Spatial pyramid coding -- Micro-texture -- SSD -- Decision-level cascade strategy; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2018.08.019
• Languages: English
• ISSNs: 0031-3203

Abstract

Highlights: Two kinds of discriminative representation combinations for face presentation attack detection. Effective combination of binocular depth with local appearance for presentation attack detection. Powerful presentation attack detection model by cascading deep network with micro-texture feature. Abstract: Three discriminative representations for face presentation attack detection are introduced in this paper. Firstly we design a descriptor called spatial pyramid coding micro-texture (SPMT) feature to characterize local appearance information. Secondly we utilize the SSD, which is a deep learning framework for detection, to excavate context cues and conduct end-to-end face presentation attack detection. Finally we design a descriptor called template face matched binocular depth (TFBD) feature to characterize stereo structures of real and fake faces. For accurate presentation attack detection, we also design two kinds of representation combinations. Firstly, we propose a decision-level cascade strategy to combine SPMT with SSD. Secondly, we use a simple score fusion strategy to combine face structure cues (TFBD) with local micro-texture features (SPMT). To demonstrate the effectiveness of our design, we evaluate the representation combination of SPMT and SSD on three public datasets, which outperforms all other state-of-the-art methods. In addition, we evaluate the representation combination of SPMT and TFBD on our dataset and excellent performance is also achieved.