Improving the Accuracy of a Score Fusion Approach Based on Likelihood Ratio in Multimodal Biometric Systems

  • Emanuela Marasco
  • Carlo Sansone
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5716)

Abstract

Multimodal biometric systems integrate information from multiple sources to improve the performance of a typical unimodal biometric system. Among the possible information fusion approaches, those based on fusion of match scores are the most commonly used. Recently, a framework for the optimal combination of match scores that is based on the likelihood ratio (LR) test has been presented. It is based on the modeling of the distributions of genuine and impostor match scores as a finite Gaussian mixture models. In this paper, we propose two strategies for improving the performance of the LR test. The first one employs a voting strategy to circumvent the need of huge datasets for training, while the second one uses a sequential test to improve the classification accuracy on genuine users.

Experiments on the NIST multimodal database confirmed that the proposed strategies can outperform the standard LR test, especially when there is the need of realizing a multibiometric system that must accept no impostors.

Keywords

Likelihood Ratio Gaussian Mixture Model Biometric System Score Vector Score Level Fusion 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

References

  1. 1.
    Jain, A., Ross, A., Prabhakar, S.: An introduction to biometric recognition. IEEE Transaction on Circuits and Systems for Video 14(1), 4–20 (2004)CrossRefGoogle Scholar
  2. 2.
    Ross, A., Jain, A.: Handbook in MultiBiometrics. Springer, Heidelberg (2008)Google Scholar
  3. 3.
    Ross, A., Jain, A.: Information fusion in biometrics. Pattern Recognition Letters 24, 2115–2125 (2003)CrossRefGoogle Scholar
  4. 4.
    Jain, A., Ross, A.: Multibiometric systems. Comm. ACM 47(1), 34–40 (2004)CrossRefGoogle Scholar
  5. 5.
    Nandakumar, K., Chen, Y., Dass, S., Jain, A.: Likelihood ratio-based biometric score fusion. IEEE Transaction on Pattern Analysis and Machine Intelligence 30(2), 342–347 (2008)CrossRefGoogle Scholar
  6. 6.
    Ma, Y., Cukic, B., Singh, H.: A classification approach to multi-biometric score fusion. In: Kanade, T., Jain, A., Ratha, N.K. (eds.) AVBPA 2005. LNCS, vol. 3546, pp. 484–493. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  7. 7.
    Nandakumar, K., Jain, A., Ross, A.: Score normalization in multimodal biometric systems. Pattern Recognition 38(12), 2270–2285 (2005)CrossRefGoogle Scholar
  8. 8.
    Dass, S., Nandakumar, K., Jain, A.: A principled approach to score level fusion in multimodal biometric systems. In: Kanade, T., Jain, A., Ratha, N.K. (eds.) AVBPA 2005. LNCS, vol. 3546, pp. 1049–1058. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  9. 9.
    Graves, S.: On the neyman-pearson theory of testing. The British Journal for the Philosophy of Science 29(1), 1–23 (1978)MathSciNetCrossRefGoogle Scholar
  10. 10.
    Lehmann, E., Romano, J.: Testing of Statistical Hypotheses. Springer, Heidelberg (2005)MATHGoogle Scholar
  11. 11.
    Bishop, C.: Pattern Recognition and Machine Learning. Springer, Heidelberg (2006)MATHGoogle Scholar
  12. 12.
    Duda, R., Hart, P., Stork, D.: Pattern Classification, 2nd edn. Wiley-Interscience, Hoboken (2001)MATHGoogle Scholar
  13. 13.
    Figuereido, M., Jain, A.: Unsupervised learning of finite mixture models. IEEE Transaction on Patterns Analysis and Machine Intelligence 24(3), 381–396 (2002)CrossRefGoogle Scholar
  14. 14.
    Nandakumar, K., Chen, Y., Jain, A., Dass, S.: Quality-based score level fusion in multimodal biometric systems. Pattern Recognition 4, 473–476 (2006)Google Scholar
  15. 15.
    Wald, A.: Sequential tests of statistical hypotheses. The annals of Mathematical Statistics 16(2), 117–186 (1945)MathSciNetCrossRefMATHGoogle Scholar
  16. 16.
    Tronci, R., Giacinto, G., Roli, F.: Combination of experts by classifiers in similarity score spaces. In: da Vitoria Lobo, N., Kasparis, T., Roli, F., Kwok, J.T., Georgiopoulos, M., Anagnostopoulos, G.C., Loog, M. (eds.) S+SSPR 2008. LNCS, vol. 5342, pp. 821–830. Springer, Heidelberg (2008)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Emanuela Marasco
    • 1
  • Carlo Sansone
    • 1
  1. 1.Dipartimento di Informatica e SistemisticaUniversità degli Studi di Napoli Federico IINapoliItaly

Personalised recommendations