Robust and interoperable fingerprint spoof detection via convolutional neural networks

Fingerprint recognition for automated border control and other high-security applications needs robust integrated anti-spoofing capability. Facing the threat of presentation attacks, two key challenges to be solved are sensor interoperability and robustness versus new fabrication materials. This paper proposes convolutional neural networks for this task and presents an exhaustive comparison on latest LivDet 2011 and 2013 databases. Apart from classical classification nets, also metric-based deep siamese networks are evaluated learning a distance metric enforcing live-spoof pairs to be of higher distance than live-live pairs. This is useful for attended enrollment scenarios where a live gallery image is available (e.g. trusted-source fingerprint reference on the passport chip). Experiments reveal remarkable accuracy for all Convolutional Neural Networks (CNNs) CaffeNet (96.5%), GoogLeNet (96.6%), Siamese (93.1%), good material robustness (max. 5.6% diff.) but weak sensor-interoperability.

[1]  Gian Luca Marcialis,et al.  LivDet 2011 — Fingerprint liveness detection competition 2011 , 2012, 2012 5th IAPR International Conference on Biometrics (ICB).

[2]  David Menotti,et al.  Deep Representations for Iris, Face, and Fingerprint Spoofing Detection , 2014, IEEE Transactions on Information Forensics and Security.

[3]  Arun Ross,et al.  Automatic adaptation of fingerprint liveness detector to new spoof materials , 2014, IEEE International Joint Conference on Biometrics.

[4]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[5]  Arun Ross,et al.  A Survey on Anti-Spoofing Schemes for Fingerprint Recognition Systems , 2014 .

[6]  Sébastien Marcel,et al.  Biometrics Evaluation Under Spoofing Attacks , 2014, IEEE Transactions on Information Forensics and Security.

[7]  Gian Luca Marcialis,et al.  LivDet 2013 Fingerprint Liveness Detection Competition 2013 , 2013, 2013 International Conference on Biometrics (ICB).

[8]  Petru Radu,et al.  Robust multimodal face and fingerprint fusion in the presence of spoofing attacks , 2016, Pattern Recognit..

[9]  Yoshua Bengio,et al.  Deep Learning of Representations: Looking Forward , 2013, SLSP.

[10]  Christoph Busch,et al.  Presentation attack detection methods for fingerprint recognition systems: a survey , 2014, IET Biom..

[11]  Yann LeCun,et al.  Learning a similarity metric discriminatively, with application to face verification , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[12]  Gian Luca Marcialis,et al.  First International Fingerprint Liveness Detection Competition - LivDet 2009 , 2009, ICIAP.

[13]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[14]  Julian Fiérrez,et al.  Fingerprint Anti-spoofing in Biometric Systems , 2014, Handbook of Biometric Anti-Spoofing.

[15]  Carlo Sansone,et al.  On the Robustness of Fingerprint Liveness Detection Algorithms against New Materials used for Spoofing , 2017, BIOSIGNALS.

[16]  Roberto de Alencar Lotufo,et al.  Evaluating software-based fingerprint liveness detection using Convolutional Networks and Local Binary Patterns , 2014, 2014 IEEE Workshop on Biometric Measurements and Systems for Security and Medical Applications (BIOMS) Proceedings.