Expert conciliation for multi modal person authentication systems by Bayesian statistics

  • E. S. Bigün
  • J. Bigün
  • B. Duc
  • S. Fischer
Audio-video Features and Fusion
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1206)


We present an algorithm functioning as a supervisor module in a multi expert decision making machine. It uses the Bayes theory in order to estimate the biases of individual expert opinions. These are then used to calibrate and conciliate expert opinions to one opinion. We present a framework for simulating decision strategies using expert opinions whose properties are easily modifiable. By using real data coming from a person authentication system using image and speech data we were able to confirm that the proposed supervisor improves the quality of individual expert decisions by reaching success rates of 99.5 %.


Expert Opinion Bayesian Statistic False Acceptance Rate False Rejection Rate Individual Expert 
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.
    J. M. Bernardo and M. F. A. Smith. Bayesian Theory. Chichester. Wiley, 1994.Google Scholar
  2. 2.
    E. S. Bigün. “Risk analysis of catastrophes using experts' judgements: An empirical study on risk analysis of major civil aircraft accidents in Europe”. European J. Operational research, Vol. 87, pp. 599–612, 1995.Google Scholar
  3. 3.
    E. S. Bigün. “Bayesian prediction based on few and dependent data”. Technical report, Department of Statistics, Stockholm University, 1996.Google Scholar
  4. 4.
    B. Duc, G. Maître, S. Fischer, and J. Bigün. “Person authentication by fusing face and speech information”. Proc. AVBPA, Springer LNCS, Bigün, et. al., Eds., 1997.Google Scholar
  5. 5.
    S. French. “Updating of belief in the light of some else's opinion”. J. R. Statist. Soc. A, Vol. 143, pp. 43–48, 1980.Google Scholar
  6. 6.
    S. French. “Group consensus probability distributions: A critical survey”. Bayesian statistics, Vol. 2, pp. 183–202, 1985.Google Scholar
  7. 7.
    V. D. Lindley, A. Tversky, and R. V. Brown. “On the reconciliation of probability assessments”. J. R. Statist. Soc. A, Vol. 142, pp. 146–180, 1979.Google Scholar
  8. 8.
    V. D. Lindley. “The improvement of probability judgments”. J. R. Statist. Soc. A, Vol. 145, pp. 117–126, 1982.Google Scholar
  9. 9.
    V. D. Lindley. “Reconciliation of discrete probability distributions”. Bayesian statistics, Vol. 2, pp. 375–390, 1985.Google Scholar
  10. 10.
    V. D Lindley and Singpurwalla. “Reliability and fault tree analysis using expert opinions”. ASAS, pp. 87–90, 1986.Google Scholar
  11. 11.
    S. Pigeon, and L. Vandendorpe The M2VTS Multimodal Face Database Proc. AVBPA, Springer LNCS, Bigün, et. al., Eds., 1997.Google Scholar
  12. 12.
    M. West. “Modelling expert opinion”. Bayesian statistics, Vol. 3, pp. 493–508, 1988.Google Scholar
  13. 13.
    R. L. Winkler, Combining probability distributions Management Science, vol. 27 pp. 479–488, (1981)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1997

Authors and Affiliations

  • E. S. Bigün
    • 1
    • 3
  • J. Bigün
    • 2
  • B. Duc
    • 2
  • S. Fischer
    • 2
  1. 1.Dep. of StatisticsStockholm UniversityStockholm
  2. 2.EPFL Signal Processing LaboratoryLausanne
  3. 3.KTH Center for Safety ResearchStockholm

Personalised recommendations