Feature Extraction for Iris Recognition Based on Optimized Convolution Kernels

  • Lubos Omelina
  • Bart Jansen
  • Milos Oravec
  • Jan Cornelis
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8157)

Abstract

Iris recognition has gained a lot of popularity for the last decades. Mainly a method based on binary iris templates found its way to real world use due to its simplicity, stability and reliability. The principle is that the unique iris structure is encoded to the bit code templates that are sufficient for high accuracy recognition. Encoding is performed by filtering a preprocessed iris image and storing only the phase information of the response to the filters. For years researchers used the 2D Gabor filters or their modifications, because these filters proved to provide the most reliable features. Despite the high recognition accuracy, the use of 2D Gabor filters faces a problem of spoofing. Recent studies show that the encoding process can be reverted and a spoofed iris can be obtained only based on the iris code. In this paper, we propose an efficient feature extraction method for iris recognition based on convolution kernels, learned from a database of irises. We show that the proposed method reaches state-of-the-art performance and can prohibit attackers from generating spoofed irises if the optimized convolution kernel is safely stored.

Keywords

iris recognition simulated annealing image filtering 

References

  1. 1.
    Daugman, J.: How Iris Recognition Works. IEEE Transactions on Circuits and Systems for Video Technology 14, 21–30 (2004)CrossRefGoogle Scholar
  2. 2.
    Daugman, J.: The importance of being random: statistical principles of iris recognition. Pattern Recognition 36, 279–291 (2003)CrossRefGoogle Scholar
  3. 3.
    Daugman, J.: Uncertainty relation for resolution in space, spatial frequency, and orien-tation optimized by two-dimensional visual cortical filters. Journal of the Optical Society of America A: Optics, Image Science, and Vision 2, 1160–1169 (1985)CrossRefGoogle Scholar
  4. 4.
    Venugopalan, S., Savvides, M.: How to Generate Spoofed Irises From an Iris Code Template. IEEE Transactions on Information Forensics and Security 6, 385–395 (2011)CrossRefGoogle Scholar
  5. 5.
    Bowyer, K.W., Hollingsworth, K., Flynn, P.J.: Image understanding for iris biometrics: A survey. Computer Vision and Image Understanding 110, 281–307 (2008)CrossRefGoogle Scholar
  6. 6.
    Masek, L.: Recognition of Human Iris Patterns for Biometric Identification (2003), http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.90.5112
  7. 7.
    Yao, P., Li, J., Ye, X., Zhuang, Z., Li, B.: Iris Recognition Algorithm Using Modified Log-Gabor Filters. In: 18th International Conference on Pattern Recognition (ICPR 2006), pp. 461–464. IEEE (2006)Google Scholar
  8. 8.
    Oppenheim, A.V., Lim, J.S.: The importance of phase in signals. Proceedings of the IEEE 69, 529–541 (1981)CrossRefGoogle Scholar
  9. 9.
    Tsai, C.C., Taur, J.S., Tao, C.W.: Iris recognition using Gabor filters optimized by the particle swarm technique. In: 2008 IEEE International Conference on Systems, Man and Cybernetics, pp. 921–926. IEEE (2008)Google Scholar
  10. 10.
    Lin, Z., Lu, B.: Iris recognition method based on the optimized Gabor filters. In: 2010 3rd International Congress on Image and Signal Processing, pp. 1868–1872 (2010)Google Scholar
  11. 11.
    Zheng, H., Su, F.: An improved iris recognition system based on gabor filters. In: IEEE International Conference on Network Infrastructure and Digital Content, IC-NIDC 2009, Beijing, China, pp. 823–827 (2009)Google Scholar
  12. 12.
    Kirkpatrick, S., Gelatt Jr., C.D., Vecchi, M.P.: Optimization by simulated annealing. In: Readings in Computer Vision: Issues, Problems, Principles, and Paradigms, pp. 606–615. Morgan Kaufmann Publishers Inc., San Francisco (1987)Google Scholar
  13. 13.
    CASIA Iris Image Database, N. L. of Pattern Recognition (NLPR), Institute of Automation (AI) Chinese Academy of Science, http://biometrics.idealtest.org
  14. 14.
    Kumar, R., Banerjee, A., Vemuri, B.C., Pfister, H.: Trainable Convolution Filters and their Application to Face Recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence 34 (2011)Google Scholar
  15. 15.
    Galbally, J.: From the iriscode to the iris: a new vulnerability of iris recognition systems. Black Hat USA 2012 (2012)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Lubos Omelina
    • 1
    • 3
  • Bart Jansen
    • 1
    • 2
  • Milos Oravec
    • 3
  • Jan Cornelis
    • 1
  1. 1.Department of Electronics and InformaticsVrije Universiteit BrusselBrusselsBelgium
  2. 2.Dept. of Future Media and ImagingiMindsGhentBelgium
  3. 3.Institute of Computer Science and MathematicsSlovak University of Technology in BratislavaSlovakia

Personalised recommendations