Feature Band Selection for Multispectral Iris Recognition

  • David Zhang
  • Zhenhua Guo
  • Yazhuo Gong


This work uses East Asian irides as research subjects and explores the possibility of clustering spectral wavelengths based on the maximum dissimilarity of iris textures. The eventual goal is to determine how many bands of spectral wavelengths will be enough for black-based iris multispectral fusion, and find these bands, which will provide an important standard for selecting bands of spectral wavelengths for iris multispectral fusion, especially for the black iris recognition of East Asians. A multispectral acquisition system is first designed for imaging the iris at narrow spectral bands in the range of 420–940 nm. Next, a set of 60 human black iris images which correspond to the right and left eyes of 30 different subjects are acquired for an analysis. Finally, we have determined that 3 clusters are enough to represent the 10 feature bands of spectral wavelengths from 545 to 940 nm, using the agglomerative clustering based on an improved multigroup two-dimensional principal component analysis [(2D)2PCA]. The experimental results suggest: (a) the number, center, and composition of clusters of spectral wavelengths and (b) the interference and potential impact of interference on the performance of iris multispectral fusion.


Mutlispectral iris (2D)2PCA Feature band Clustering 


  1. Baraniuk RG, Jones DL (1993) A signal-dependent time-frequency representation: optimal kernel design. IEEE Trans Signal Process 41(4):1589–1602MATHCrossRefGoogle Scholar
  2. Boyce CK (2006) Multispectral iris recognition analysis: techniques and evaluation. Doctoral dissertation, West Virginia UniversityGoogle Scholar
  3. Burge MJ, Monaco MK (2009) Multispectral iris fusion for enhancement, interoperability, and cross wavelength matching. In: SPIE defense, security, and sensing, pp 73341DGoogle Scholar
  4. Cover TM, Thomas JA (1991) Elements of information theory. Wiley, New YorkGoogle Scholar
  5. Daugman JG (1993) High confidence visual recognition of persons by a test of statistical independence. IEEE Trans Pattern Anal Mach Intell 15(11):1148–1161CrossRefGoogle Scholar
  6. Daugman J (2007) New methods in iris recognition. IEEE Trans Syst Man Cybern B 37(5):1167–1175CrossRefGoogle Scholar
  7. Everitt B, Landau S, Leese M (2001) Cluster analysis, 4th edn. Edward Arnold, LondonMATHGoogle Scholar
  8. Foote J (2000) Automatic audio segmentation using a measure of audio novelty. In: IEEE international conference on multimedia and expo, vol 1. IEEE, Piscataway. pp 452–455Google Scholar
  9. Franssen L, Coppens JE, van den Berg TJ (2008) Grading of iris color with an extended photographic reference set. J Optom 1(1):36–40CrossRefGoogle Scholar
  10. Ghosal S, Van Der Vaart AW (2001) Entropies and rates of convergence for maximum likelihood and Bayes estimation for mixtures of normal densities. Ann Stat 1233–1263Google Scholar
  11. Ghosal S, Van Der Vaart A (2007) Posterior convergence rates of Dirichlet mixtures at smooth densities. Ann Stat 35(2):697–723MATHCrossRefGoogle Scholar
  12. Ghosal S, Ghosh JK, Ramamoorthi RV (1999) Posterior consistency of Dirichlet mixtures in density estimation. Ann Stat 27(1):143–158MATHMathSciNetCrossRefGoogle Scholar
  13. Hollingsworth K, Bowyer KW, Flynn PJ (2009) Pupil dilation degrades iris biometric performance. Comput Vis Image Underst 113(1):150–157CrossRefGoogle Scholar
  14. Johnson DH, Sinanovi S (2001) Symmetrizing the Kullback-Leibler distance. IEEE Trans Inf TheoryGoogle Scholar
  15. Li Z, Sun F (2005) Pupillary response induced by stereoscopic stimuli. Exp Brain Res 160(3):394–397CrossRefGoogle Scholar
  16. Liu Z, Yan JQ, Zhang D, Li QL (2007) Automated tongue segmentation in hyperspectral images for medicine. Appl Opt 46(34):8328–8334CrossRefGoogle Scholar
  17. Ozawa K (1983) CLASSIC: a hierarchical clustering algorithm based on asymmetric similarities. Pattern Recognit 16(2):201–211MATHCrossRefGoogle Scholar
  18. Park JH, Kang MG (2007) Multispectral iris authentication system against counterfeit attack using gradient-based image fusion. Opt Eng 46(11):117003Google Scholar
  19. Ross A, Pasula R, Hornak L (2006) Exploring multispectral iris recognition beyond 900 nm. In: Proceedings of the 2006 conference on computer vision and pattern recognition workshop, p 51Google Scholar
  20. Sun FC, Chen LY, Zhao XZ (1998) Pupillary responses evoked by spatial patterns. Acta Physiol Sin 50(1):67–74Google Scholar
  21. Theodoridis S, Koutroumbas K (2006) Pattern recognition, 3rd edn. Elsevier, AmsterdamMATHGoogle Scholar
  22. Thornton J, Savvides M, Kumar V (2007) A Bayesian approach to deformed pattern matching of iris images. IEEE Trans Pattern Anal Mach Intell 29(4):596–606CrossRefGoogle Scholar
  23. Tokdar ST (2006) Posterior consistency of Dirichlet location-scale mixture of normals in density estimation and regression. Sankhya Indian J Stat 67: 90–110Google Scholar
  24. Vatsa M, Singh R, Noore A (2008) Improving iris recognition performance using segmentation, quality enhancement, match score fusion, and indexing. IEEE Trans Syst Man Cybern B Cybern 38(4):1021–1035CrossRefGoogle Scholar
  25. Vilaseca M, Pujol J, Arjona M, de Lasarte M (2006) Multispectral system for reflectance reconstruction in the near-infrared region. Appl Opt 45(18):4241–4253CrossRefGoogle Scholar
  26. Vilaseca M, Mercadal R, Pujol J, Arjona M, de Lasarte M, Huertas R, Melgosa M, Imai FH (2008) Characterization of the human iris spectral reflectance with a multispectral imaging system. Appl Opt 47(30):5622–5630CrossRefGoogle Scholar
  27. Wilkerson CL, Syed NA, Fisher MR, Robinson NL, Albert DM (1996) Melanocytes and iris color: light microscopic findings. Arch Ophthalmol 114(4):437–442CrossRefGoogle Scholar
  28. Zuo W, Zhang D, Wang K (2006) Bidirectional PCA with assembled matrix distance metric for image recognition. IEEE Trans Syst Man Cybern B Cybern 36(4):863–872CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2016

Authors and Affiliations

  1. 1.Biometrics Research CentreThe Hong Kong Polytechnic UniversityHung HomHong Kong SAR
  2. 2.Shenzhen Key Laboratory of Broadband Network & Multimedia, Graduate School at ShenzhenTsinghua UniversityShenzhenChina
  3. 3.University of Shanghai for Science and TechnologyShanghaiChina

Personalised recommendations