Ridge-Slope-Valley Feature for Fingerprint Liveness Detection

Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 322)

Abstract

Attacking fingerprint-based biometric systems by presenting fake fingers is a serious threat for unattended devices. In this work, we introduce a novel algorithm, by extracting features along the fingerprint curves, to discriminate between fake fingers and real ones on static images. Pairs of mean value and standard deviation are sampled from the ridge, slope and valley of the curves. Then bag-of-words model is used to select cluster centers and form a 128-dimension feature of words’ frequency. We test our method on a dataset collected by Chinese Academy of Science, which contains 960 live fingerprints and 960 fake ones made by silicon. Though the fake fingerprints is too verisimilar to be distinguished by naked eyes, we still get an accuracy of 98.85 %. Because our method is based on single static fingerprint image, it can be freely embedded into existing fingerprint-based biometric systems.

Keywords

Fingerprint liveness detection Bag-of-words model Image texture analysis. 

Notes

Acknowledgements

This research was supported by the National Natural Science Foundation of China (61201271, 61301269), the Fundamental Research Funds for the Central Universities (ZYGX2013J019, ZYGX2013J017), Sichuan Science and Technology Support Program (cooperated with the Chinese Academy of Sciences) (2012JZ001), and Science and Technology Support Program of Sichuan Province, China (2014GZX0009).

References

  1. 1.
    Ratha NK, Connell JH, Bolle RM (2001) Enhancing security and privacy in biometrics-based authentication systems. IBM Syst J 40(3):614–634 Google Scholar
  2. 2.
    Coli P, Marcialis GL, Roli F (2007) Power spectrum-based fingerprint vitality detection. In: IEEE workshop on automatic identification advanced technologies. IEEE, pp 169–173Google Scholar
  3. 3.
    Abhyankar AS, Schuckers SC (2004) A wavelet-based approach to detecting liveness in fingerprint scanners. In: Defense and security. International society for optics and photonics, pp. 278–286Google Scholar
  4. 4.
    Moon YS, Chen JS, Chan KC, So K, Woo KC (2005) Wavelet based fingerprint liveness detection. Electron Lett 41(20):1112–1113CrossRefGoogle Scholar
  5. 5.
    Tan B, Schuckers S (2006) Liveness detection for fingerprint scanners based on the statistics of wavelet signal processing. In: Conference on computer vision and pattern recognition workshop (CVPRW’06). IEEE, pp 26–26Google Scholar
  6. 6.
    Nikam SB, Agarwal S (2008) Fingerprint liveness detection using curvelet energy and co-occurrence signatures. In: Fifth international conference on computer graphics, imaging and visualisation (CGIV’08). IEEE, pp 217–222Google Scholar
  7. 7.
    Choi H, Kang R, Choi K, Jin ATB, Kim J (2009) Fake-fingerprint detection using multiple static features. Opt Eng 48(4):047202–047202CrossRefGoogle Scholar
  8. 8.
    Derakhshani R, Schuckers SAC, Hornak LA, O’Gorman L (2003) Determination of vitality from a non-invasive biomedical measurement for use in fingerprint scanners. Pattern Recogn 36(2):383–396CrossRefGoogle Scholar
  9. 9.
    Parthasaradhi STV, Derakhshani R, Hornak LA, Schuckers SAC (2005) Time-series detection of perspiration as a liveness test in fingerprint devices. IEEE Trans Syst Man Cybern Part C 35(3):335–343CrossRefGoogle Scholar
  10. 10.
    Tan B, Schuckers S (2010) Spoofing protection for fingerprint scanner by fusing ridge signal and valley noise. Pattern Recogn 43(8):2845–2857MATHCrossRefGoogle Scholar
  11. 11.
    Hong L, Wan Y, Jain A (1998) Fingerprint image enhancement: algorithm and performance evaluation. IEEE Trans Pattern Anal Mach Intell 20(8):777–789CrossRefGoogle Scholar
  12. 12.
    Wu X (1991) An efficient antialiasing technique. ACM SIGGRAPH Comput Graph 25(4):143–152CrossRefGoogle Scholar
  13. 13.
    Fake fingerprint database from Chinese Academy of Sciences. http://www.fingerpass.csdb.cn
  14. 14.
    Ojala T, Pietikäinen M, Harwood D (1996) A comparative study of texture measures with classification based on featured distributions. Pattern Recogn 29(1):51–59 Google Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  1. 1.School of Electronic EngineeringUniversity of Electronic Science and Technology of ChinaChengduPR China

Personalised recommendations