Quantitative Evaluation of Normalization Techniques of Matching Scores in Multimodal Biometric Systems

  • Y. N. Singh
  • P. Gupta
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4642)


This paper attempts to make an quantitative evaluation of available normalization techniques of matching scores in multimodal biometric systems. Two new normalization techniques Four Segments Piecewise Linear (FSPL) and Linear Tanh Linear (LTL) have been proposed in this paper. FSPL normalization techniques divides the region of genuine and impostor scores into four segments and maps each segment using piecewise linear function while LTL normalization techniques maps the non-overlap region of genuine and impostor score distributions to a constant function and overlap region using tanh estimator. The effectiveness of each technique is shown using EER and ROC curves on IITK database of having more than 600 people on following characteristics: face, fingerprint, and offline-signature. The proposed normalization techniques perform better and particularly, LTL normalization is efficient and robust.


  1. 1.
    Jain, A.K., Ross, A.: Information Fusion in Biometrics. Pattern Recognition Letters, Special Issues on Multimodal Biometrics, 2115–2125 (2003)Google Scholar
  2. 2.
    Snelick, R., Indovina, M., Yen, J., Mink, A.: Multimodal Biometrics: Issues in Design and Testing. In: ICMI 2003, Canada, pp. 68–72 (2003)Google Scholar
  3. 3.
    Jain, A.K., Ross, A.: Learning User Specific Parameters in a Multimodal Biometric Systems. In: ICIP. Proc. Inter. Conf. on Image Processing, pp. 57–60 (2002)Google Scholar
  4. 4.
    Hassanien, A.E., Ali, J.M.: An Iris Recognition System to Enhance E-security Environment Based on Wavelet Theory. AMO 5(2), 93–104 (2003)zbMATHMathSciNetGoogle Scholar
  5. 5.
    Thai, R.: Fingerprint Image Enhancement and Minutiae Extraction. Technical Report, The University of Western Australia (2003)Google Scholar
  6. 6.
    Ismail, M.A., Gad, S.: Off-line Arabic Signature Recognition and Verification. Pattern Recognition 33, 1727–1740 (2000)CrossRefGoogle Scholar
  7. 7.
    Jain, A.K., Nandakumara, K., Ross, A.: Score Normalization in Multimodal Biometric Systems. Pattern Recognition 38, 2270–2285 (2005)CrossRefGoogle Scholar
  8. 8.
    Snelick, R., Uludag, U., Mink, A., Indovina, M., Jain, A.K.: Large-Scale Evaluation of Multimodal Biometric Authentication Using State-of-the-Art Systems. IEEE Trans. on PAMI 27(3), 450–455 (2005)Google Scholar
  9. 9.
    Grubbs, F.E.: Procedures for Detecting Outlying Observations in Samples. Technometrics 11(1), 121 (1969)CrossRefGoogle Scholar
  10. 10.
    Hampel, F.R., Ronchetti, E.M., Rousseeuw, P.J., Stahel, W.A.: Robust Statistics: The Approach Based on Influence Functions. Wiley, New York (2005)Google Scholar
  11. 11.
    Bolle, R.M., Pankanti, S., Ratha, N.K.: Evaluation Techniques for Biometrics-Based Authentication Systems (FRR). In: Proc. of 15th International Conference Pattern Recognition, vol. 2, pp. 831–837 (2000)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2007

Authors and Affiliations

  • Y. N. Singh
    • 1
  • P. Gupta
    • 1
  1. 1.Department of Computer Science and Engineering, Indian Institute of Technology Kanpur, Kanpur-208016India

Personalised recommendations