Robust multimodal face and fingerprint fusion in the presence of spoofing attacks. (February 2016)

• Record Type: Journal Article
• Authors: Wild, Peter; Radu, Petru; Chen, Lulu; Ferryman, James
• Is Part Of: Pattern recognition. Volume 50(2016:Feb.)
• Page Start: 17
• Page End: 25
• Publication Date: 2016-02
• Subjects: Multibiometrics -- Anti-spoofing -- 1-Median; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2015.08.007
• Languages: English
• ISSNs: 0031-3203

Abstract

Abstract: Anti-spoofing is attracting growing interest in biometrics, considering the variety of fake materials and new means to attack biometric recognition systems. New unseen materials continuously challenge state-of-the-art spoofing detectors, suggesting for additional systematic approaches to target anti-spoofing. By incorporating liveness scores into the biometric fusion process, recognition accuracy can be enhanced, but traditional sum-rule based fusion algorithms are known to be highly sensitive to single spoofed instances. This paper investigates 1-median filtering as a spoofing-resistant generalised alternative to the sum-rule targeting the problem of partial multibiometric spoofing where m out of n biometric sources to be combined are attacked. Augmenting previous work, this paper investigates the dynamic detection and rejection of liveness-recognition pair outliers for spoofed samples in true multi-modal configuration with its inherent challenge of normalisation. As a further contribution, bootstrap aggregating (bagging) classifiers for fingerprint spoof-detection algorithm is presented. Experiments on the latest face video databases (Idiap Replay-Attack Database and CASIA Face Anti-Spoofing Database) and fingerprint spoofing database (Fingerprint Liveness Detection Competition 2013) illustrate the efficiency of proposed techniques. Abstract : Highlights: We examine spoofing robustness in multibiometrics attacking m out of n instances. 1-Median filtering detecting score anomalies is proposed for spoof-resistant fusion. In contrast to sum-rule, operation with stable m -spoof performance can be achieved. Best performance (84%) for bagging of classifiers approach on LivDet2013 CrossMatch.