Skip to content

Face anti-spoofing: Multi-spectral approach

N/ACitations
Citations of this article
12Readers
Mendeley users who have this article in their library.
Get full text

Abstract

With the wide applications of face recognition, spoofing attack is becoming a big threat to their security.Conventional face recognition systems usually adopt behavioral challenge-response or texture analysis methods to resist spoofing attacks, however, these methods require high user cooperation and are sensitive to the imaging quality and environments. In this chapter, we present a multi-spectral face recognition system working in VIS (Visible) and NIR (Near Infrared) spectrums, which is robust to various spoofing attacks and user cooperation free. First, we introduce the structure of the system from several aspects including: imaging device, face landmarking, feature extraction, matching, VIS, and NIR sub-systems. Then the performance of the multi-spectral system and each subsystem is evaluated and analyzed. Finally, we describe the multi-spectral image-based anti-spoofing module, and report its performance under photo attacks. Experiments on a spoofing database show the excellent performance of the proposed system both in recognition rate and anti-spoofing ability. Compared with conventional VIS face recognition system, the multi-spectral system has two advantages: (1) By combining the VIS and NIR spectrums, the system can resist VIS photo and NIR photo attacks easily. And users’ cooperation is no longer needed, making the system user friendly and fast. (2) Due to the precise key-point localization, Gabor feature extraction and unsupervised learning, the system is robust to pose, illumination and expression variations. Generally, its recognition rate is higher than the VIS subsystem.

Cite

CITATION STYLE

APA

Yi, D., Lei, Z., Zhang, Z., & Li, S. Z. (2014). Face anti-spoofing: Multi-spectral approach. In Advances in Computer Vision and Pattern Recognition (Vol. 49, pp. 83–102). Springer-Verlag London Ltd. https://doi.org/10.1007/978-1-4471-6524-8_5

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Save time finding and organizing research with Mendeley

Sign up for free