Gaussian Mixture Models for Supervised Classification of Remote Sensing Multispectral Images

  • Ana Claudia Oliveira de Melo
  • Ronei Marcos de Moraes
  • Liliane dos Santos Machado
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2905)


This paper proposes the use of Gaussian Mixture Models as a supervised classifier for remote sensing multispectral images. The main advantage of this approach is provide more adequated adjust to several statistical distributions, including non-symmetrical statistical distributions. We present some results of this method application over a real image of an area of Tapajós River in Brazil and the results are analysed according to a reference image. We perform also a comparison with Maximum Likelihood classifier. The Gaussian Mixture classifier obtained best adjust about image data and best classification performance too.


Remote Sensing Bayesian Information Criterion Gaussian Mixture Model Real Image Multispectral Image 
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.


  1. 1.
    Kent, J.T., Mardia, K.V.: Spatial classification using fuzzy membership models. IEEE Trans. on Patt. Anal. and Mach. Intel. 10, 659–671 (1988)zbMATHCrossRefGoogle Scholar
  2. 2.
    Ho, T.K., Hull, J.J., Srihari, S.N.: Decision combination in multiple classifier systems. IEEE Trans. on Patt. Anal. and Mach. Intel. 16, 66–75 (1994)CrossRefGoogle Scholar
  3. 3.
    Simpson, P.K.: Artificial Neural Systems. Pergamon Press, New York (1990)Google Scholar
  4. 4.
    Moraes, R.M., Sandri, S.A., Banon, G.J.F.: Expert Systems Architecture for Image Classification Using Mathematical Morphology Operators. Information Science 142, 7–21 (2002)zbMATHCrossRefGoogle Scholar
  5. 5.
    Yang, M.H., Ahuja, N.: Gaussian Mixture Model for Human Skin Color and Its Application in Image and Video Databases. In: Proc. of the SPIE, Conf. on Storage and Retrieval for Image and Video Databases, San Jose, vol. 3656, pp. 458–466 (1999)Google Scholar
  6. 6.
    Tran, D., Pham, T., Wagner, M.: Speaker recognition using Gaussian mixture models and relaxation labeling. In: Proceedings of the 3rd World Multiconference on Systemetics, Cybernetics and Informatics/ The 5th Int. Conf. Information Systems Analysis and Synthesis (SCI/ISAS 1999), USA, vol. 6, pp. 383–389 (1999)Google Scholar
  7. 7.
    Caillol, H., Pieczynski, W., Hillon, A.: Estimation of fuzzy Gaussian mixture and unsupervised statistical image segmentation. IEEE Trans. on Image Proces. 6, 425–440 (1977)CrossRefGoogle Scholar
  8. 8.
    Pieczynski, W., Bouvrais, J., Michel, C.: Estimation of generalized mixture in the case of correlated sensors. IEEE Trans. on Image Proces. 9, 308–311 (2000)CrossRefGoogle Scholar
  9. 9.
    Schwartz, G.: Estimating the Dimension of a Model. The Ann. of Stat. 6, 461–464 (1978)CrossRefGoogle Scholar
  10. 10.
    Dempster, A.P., Laird, N.M., Rubin, D.B.: Maximum Likelihood from Incomplete Data via the EM Algorithm. J.R.Statis.Soc. B 39, 1–38 (1977)zbMATHMathSciNetGoogle Scholar
  11. 11.
    Akaike, H.: A new look at the statistical identification model. IEEE Trans. on Automatic Control 19, 716–723 (1974)zbMATHMathSciNetCrossRefGoogle Scholar
  12. 12.
    Biernacki, C., Govaert, G.: Choosing models in model-based clustering and discriminant analysis. Technical Report INRIA no. 3509 (1998)Google Scholar
  13. 13.
    Rabiner, L.R.: A Tutorial on Hidden Markov Models and Selected Application in Speech Recognition. Proceedings of the IEEE 77 (1989)Google Scholar
  14. 14.
    Johnson, R.A., Wichern, D.W.: Applied Multivariate Statistical Analysis. Prentice-Hall, Englewood Cliffs (1998)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2003

Authors and Affiliations

  • Ana Claudia Oliveira de Melo
    • 1
  • Ronei Marcos de Moraes
    • 1
  • Liliane dos Santos Machado
    • 2
  1. 1.Department of StatisticsUFPB - Federal University of ParaíbaJoão PessoaBrazil
  2. 2.Department of Computer SciencesUFPB - Federal University of ParaíbaJoão PessoaBrazil

Personalised recommendations