Advertisement

DFT-Based Feature Extraction and Intensity Mapped Contrast Enhancement for Enhanced Iris Recognition

  • S. M. Rakesh
  • G. S. P. Sandeep
  • K. Manikantan
  • S. Ramachandran
Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 221)

Abstract

Iris Recognition (IR) under varying contrast conditions with low gradience is challenging, and exacting contrast invariant features is an effective approach to solve this problem. In this paper, we propose two novel techniques viz., Intensity Mapped Contrast Enhancement (IMCE) and Double symmetric rectangular hyperbolic based DFT (DsrhDFT) extraction. IMCE is a preprocessing technique used to increase the gradience between brighter and darker pixels of an image, thereby obtaining the salient iris features. DsrhDFT is used to extract prominent shift-invariant features, and a Binary Particle Swarm Optimization (BPSO) based feature selection algorithm is used to search the feature space for optimal feature subset. Individual stages of the IR system are examined and an attempt is made to improve each stage. Experimental results obtained by applying the proposed algorithm on Phoenix, MMU and IITD iris databases, show the promising performance of the IMCE+DsrhDFT for iris recognition. A significant increase in the recognition rate and a substantial reduction in the number of features is observed.

Keywords

Iris recognition Feature extraction Feature selection Discrete fourier transform Binary particle swarm optimization 

References

  1. 1.
    Jain A, Bolle R, Pankanti S (2000) Biometrics: the future of identification. IEEE comput soc 33(2):46–49CrossRefGoogle Scholar
  2. 2.
    Daugman J (2004) How Iris recognition works. IEEE Trans Circuits Syst Video Technol 14(1):21–30Google Scholar
  3. 3.
    Daugman J (2007) New methods in Iris recognition. IEEE Trans Syst Man Cybern 37(5):1167–1175Google Scholar
  4. 4.
    Li M, Yunhong W, Tan T (2002) Iris recognition using circular symmetric filters. In: Proceedings of \({16^{{\rm {th}}}}\) international conference on pattern recognition, vol 2, pp 414–417Google Scholar
  5. 5.
    Kevin B, Karen H, Flynn, P (2008) Image understanding for Iris biometrics: A survey. Comput Vis Image Underst 110:281–307Google Scholar
  6. 6.
    Sung H, Lim J, Park J-H, Lee Y (2004) Iris recognition using collarette boundary localization. In: \({17^{{\rm {th}}}}\) international conference on pattern recognition, vol 4, pp 857–860Google Scholar
  7. 7.
    Monro D, Rakshit S, Zhang D (2007) DCT-based Iris recognition. IEEE Trans Pattern Anal Mach Intell 29(4):586–595Google Scholar
  8. 8.
    Kumar A, Passi A (2010) Comparison and combination of Iris matchers for reliable personal authentication. Pattern Recogn 43(3):1016–1026Google Scholar
  9. 9.
    Kennedy J, Eberhart R (1997) A discrete binary version of the particle swarm algorithm. IEEE Int Conf Syst Man Cybern 5:4104–4108Google Scholar
  10. 10.
    Duda R, Hart P, Stork D (2000) Pattern classification, 2nd edn. Wiley-Interscience, New YorkGoogle Scholar
  11. 11.
    Gonzalez R, Woods R (2008) Digital image processing, 3rd edn. Prentice Hall, Upper Saddle RiverGoogle Scholar
  12. 12.
    Wang D, Vagnucci AH (1983) Digital image enhancement. Comput Vis Graph Image Process 24(3):363–381CrossRefGoogle Scholar
  13. 13.
    Sun C, Ruan SJ, Shie MC, Pai TW (2005) Dynamic contrast enhancement based on histogram specification. IEEE Trans Consum Electron 51(4):1300–1305CrossRefGoogle Scholar
  14. 14.
    Badamchizadeh MA, Aghagolzadeh A (2004) Comparative study of unsharp masking methods for image enhancement. In: 3rd international conference on image and graphics, pp 27–30Google Scholar
  15. 15.
    Imtiaz H (2011) A spectral domain local feature extraction algorithm for face recognition. Int J Secur 5(2):62–73Google Scholar
  16. 16.
    Kennedy J, Eberhart RC (1995) Particle swarm optimization. In: IEEE international conference on neural network, vol 4, issue 4, pp 1942–1948Google Scholar
  17. 17.
    Ramadan RM, Abdel-Kader RF (2009) Face recognition using particle swarm optimization-based selected features. Int J Signal Process Image Process Pattern Recognit 2(2):57–59Google Scholar
  18. 18.
    Phoenix Database, http://www.inf.upol.cz/iris/
  19. 19.
  20. 20.
  21. 21.

Copyright information

© Springer India 2013

Authors and Affiliations

  • S. M. Rakesh
    • 1
  • G. S. P. Sandeep
    • 1
  • K. Manikantan
    • 1
  • S. Ramachandran
    • 2
  1. 1.M S Ramaiah Institute of TechnologyBangaloreIndia
  2. 2.S J B Institute of TechnologyBangaloreIndia

Personalised recommendations