Bayesian Approach to Mixture Models for Discrimination

  • Keith Copsey
  • Andrew Webb
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1876)


This paper develops a Bayesian mixture model approach to discrimination. The specific problem considered is the classification of mobile targets, from Inverse Synthetic Aperture Radar images. However, the algorithm developed is relevant to the generic classification problem. We model the data measurements from each target as a mixture distribution. A Bayesian formalism is adopted, and we obtain posterior distributions for the parameters of our mixture models. The distributions obtained are too complicated for direct analytical use in a classifier, so a Markov chain Monte Carlo (MCMC) algorithm is used to provide samples from the distributions. These samples are then used to make classifications of future data.


Bayesian inference Discrimination Inverse Synthetic ApertureRadar Markov chain Monte Carlo Mixture models Target recognition 


  1. [1]
    N.M. Adams and D.J. Hand. Comparing classifiers when the misclassification costs are uncertain. Pattern Recognition, 7:1139–1148, 1999.CrossRefGoogle Scholar
  2. [2]
    G. Casella and E. George. Explaining the Gibbs sampler. The American Statistician, 46(3):167–174, 1992.CrossRefMathSciNetGoogle Scholar
  3. [3]
    G. Casella and C.P. Robert. Rao-Blackwellisation of sampling schemes. Biometrika, 83(1):81–94, 1996.zbMATHCrossRefMathSciNetGoogle Scholar
  4. [4]
    K.D. Copsey and A.R. Webb. Bayesian approach to mixture models for target recognition. In preparation, 2000.Google Scholar
  5. [5]
    M.H. DeGroot. Optimal Statistical Decisions. McGraw-Hill, 1970.Google Scholar
  6. [6]
    W. Denton and A. Britton. The classification of vehicles in MMW imagery. Proceedings of Symposium on Non-cooperative airborne target identification using RADAR, NATO SCI Panel, 1998.Google Scholar
  7. [7]
    W.R. Gilks, S. Richardson, and D.J. Spiegelhalter. Markov chain Monte Carlo in Practice. Chapman and Hall, 1996.Google Scholar
  8. [8]
    D.J. Hand. Construction and Assessment of Classification Rules. John Wiley, Chichester, 1997.zbMATHGoogle Scholar
  9. [9]
    T. Hastie and R. Tibshirani. Discriminant analysis by Gaussian mixtures. Journal of the Royal Statistical Society, Series B, 58:155–176, 1996.zbMATHMathSciNetGoogle Scholar
  10. [10]
    K.B. Laskey. A Bayesian approach to clustering and classification. Proceedings of IEEE Int. Conf. Syst. Man and Cybernetics, Charlottesville, Va, pages 179–183, October 1991.Google Scholar
  11. [11]
    M. Lavine and M. West. A Bayesian method for classification and discrimination. Canadian Journal of Statistics, 20:451–461, 1992.zbMATHCrossRefMathSciNetGoogle Scholar
  12. [12]
    S. Richardson and P.J. Green. On Bayesian analysis of mixtures with an unknown number of components. Journal of the Royal Statistical Society, Series B, 59:731–792, 1997.zbMATHCrossRefMathSciNetGoogle Scholar
  13. [13]
    B.W. Silverman. Density Estimation for Statistics and Data Analysis. Chapman and Hall, 1986.Google Scholar
  14. [14]
    A.R. Webb. Statistical Pattern Recognition. Arnold, London, 1999.Google Scholar
  15. [15]
    A.R. Webb. Gamma mixture models for target recognition. Pattern Recognition, to appear, 2000.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2000

Authors and Affiliations

  • Keith Copsey
    • 1
  • Andrew Webb
    • 1
  1. 1.DERA MalvernMalvern

Personalised recommendations