Role of Statistical Dependence Between Classifier Scores in Determining the Best Decision Fusion Rule for Improved Biometric Verification

  • Krithika Venkataramani
  • B. V. K. Vijaya Kumar
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4105)


Statistical dependence between classifier scores has been shown to affect the verification accuracy for certain decision fusion rules (e.g.,‘majority’, ‘and’, ‘or’). In this paper, we investigate what are the best decision fusion rules for various statistical dependences between classifiers and check whether the best accuracy depends on the statistical dependence. This is done by evaluating accuracy of decision fusion rules on three jointly Gaussian scores with various covariances. It is found that the best decision fusion rule for any given statistical dependence is one of the three major rules – ‘majority’,‘and’, ‘or’. The correlation coefficient between the classifier scores can be used to predict the best decision fusion rule, as well as for evaluation of how well-designed the classifiers are. This can be applied to biometric verification; and it is shown using the NIST 24 fingerprint database and the AR face database that the prediction and evaluation agree.


Statistical Dependence Minimum Probability Good Rule False Acceptance Rate False Reject Rate 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Kuncheva, L.I., Whitaker, C.J., Shipp, C.A., Duin, R.P.W.: Limits on the majority vote accuracy in classifier fusion. Pattern Analysis and Applications 6, 22–31 (2003)MATHCrossRefMathSciNetGoogle Scholar
  2. 2.
    Demikelker, M., Altincay, H.: Plurality voting-based multiple classifier systems: statistically independent with respect to dependent classifier sets. Pattern Recognition 35, 2365–2379 (2002)CrossRefGoogle Scholar
  3. 3.
    Venkataramani, K., Vijaya Kumar, B.V.K.: Conditionally dependent classifier fusion using and rule for improved biometric verification. In: Singh, S., Singh, M., Apte, C., Perner, P. (eds.) ICAPR 2005. LNCS, vol. 3687, pp. 277–286. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  4. 4.
    Venkataramani, K., VijayaKumar, B.V.K.: Or rule fusion of conditionally dependent correlation filter based classifiers for improved biometric verification. In: OPR XVII, Proc. SPIE, vol. 6245, pp. 105–116 (2006)Google Scholar
  5. 5.
    Liu, Y., Yao, X.: Ensemble learning via negative correlation. Neural Networks 12 (1999)Google Scholar
  6. 6.
    Kuncheva, L.I., Whitaker, C.J.: Measures of diversity in classifier ensembles. Machine Learning 51, 181–207 (2003)MATHCrossRefGoogle Scholar
  7. 7.
    Watson, C.I.: NIST special database 24 - live-scan digital video fingerprint database (1998)Google Scholar
  8. 8.
    Martinez, A.M., Benavente, R.: The AR face database. Technical Report 24, CVC (1998)Google Scholar
  9. 9.
    Varshney, P.K.: Distributed detection and data fusion. Springer, New York (1997)Google Scholar
  10. 10.
    VijayaKumar, B.V.K., Carlson, D.W., Mahalanobis, A.: Optimal trade-off synthetic discriminant function filters for arbitrary devices. Optics Letters 19, 1556–1558 (1994)CrossRefGoogle Scholar
  11. 11.
    Venkataramani, K., VijayaKumar, B.V.K.: Performance of composite correlation filters in fingerprint verification. Optical Engineering 43, 1820–1827 (2004)CrossRefGoogle Scholar
  12. 12.
    Hastie, T., et al.: The elements of statistical learning, 1st edn. Springer, Heidelberg (2003)Google Scholar
  13. 13.
    Zheng, W., Zou, C., Zhao, L.: Real-time face recognition using Gram-Schmidt orthogonalization for LDA. In: Int. Conf. on Pattern Recognition, pp. 403–406 (2004)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Krithika Venkataramani
    • 1
  • B. V. K. Vijaya Kumar
    • 1
  1. 1.ECE DepartmentCyLab, Carnegie MellonPittsburghUSA

Personalised recommendations