Advertisement

Analysis and Modelling of Diversity Contribution to Ensemble-Based Texture Recognition Performance

  • Samuel Chindaro
  • Konstantinos Sirlantzis
  • Michael Fairhurst
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3541)

Abstract

The RGB colour space is prominent as a colour representation and display scheme, although a number of other colour spaces have been developed over the years each with its own advantages and shortcomings with regard to its usefulness for colour/texture recognition. However, the recent advent of multiple classifier systems provides the unique opportunity to exploit the diverse information encapsulated in the different colour representations in a systematic fashion. In this paper we propose the use of classifier combination schemes which utilise information from different colour domains. We subsequently use suitable measures to investigate the diversity of the information infused by the different colour spaces. Experiments with two 40-class colour/texture datasets show the benefit of our multiple classifier approach, and reveal the existence of strong correlations between the accuracy achieved and the diversity measures. Finally, we illustrate, using quadratic regression, that there is significant scope to build and explore further (potentially causal) models of the observed relations between ensemble performance and diversity metrics. Our results point towards the use of diversity along with other statistical measures as possible predictors of the ensemble behaviour.

Keywords

Colour Space Markov Random Field Colour Representation Fisher Linear Discriminant Multiple Classifier System 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Garcia, M.A., Puig, D.: Improving Texture Pattern Recognition by Integration of Multiple Texture Feature Extraction Methods. In: Proc. 16 th International Conference on Pattern Recognition (ICPR 2002), Quebec City, QC, Canada, vol. 3 (2002)Google Scholar
  2. 2.
    Singh, M., Markou, M., Singh, S.: Colour Image Texture Analysis: Dependence on Colour Spaces. In: Proc. 15th Int. Conf. on Pat. Recog (ICPR 2002), Canada (2002)Google Scholar
  3. 3.
    Chindaro, S., Deravi, F.: Directional Properties of Colour Co-occurrence Matrices for Lip Location and Segmentation, August 17. LNCS, pp. 84–85 (2001)Google Scholar
  4. 4.
    Kuncheva, L.I., Whitaker, C.J.: Measures of diversity in classifier ensembles. Machine Learning 51, 181–207 (2003)zbMATHCrossRefGoogle Scholar
  5. 5.
    Tumer, K., Ghosh, J.: Error correlation and reduction in ensemble classifiers. In: Connection Science, vol. 8(3/4), pp. 127–161. Springer, London (1996)Google Scholar
  6. 6.
    Cunningham, P., Carney, J.: Diversity versus quality in classification ensembles based on feature selection. Technical Report TCD-CS-200-02, Department of Computer Science, Trinity College Dublin (2000)Google Scholar
  7. 7.
    Patridge, D., Krazanowski, W.J.: Software Diversity: Practical Statistics for its measurement and exploitation. Inf. and Software Techn. 39, 707–717 (1997)CrossRefGoogle Scholar
  8. 8.
    Foely, J., Van Dam, A., Feiner, S., Hughes, J.: Computer Graphics. Principals and Practice Addison Wesley, Reading (1990)Google Scholar
  9. 9.
    Cross, R.G., Jain, A.K.: Markov Random Fields Texture Models. IEEE Trans. on Patt. An. and Mach. Intelligence PAMI-5(1), 25–39 (1983)Google Scholar
  10. 10.
    Panjwani, D.K., Healey, G.: Markov Random fields for Unsupervised Segmentation of Textured Colour Images. IEEE Trans. On Pattern Analysis and Machine Intelligence 17(10) (October 1995)Google Scholar
  11. 11.
    Chindaro, S., Sirlantzis, K., Deravi, F.: Colour Space Fusion for Texture Recognition. In: Proc. of the 4th EURASIP Conf. on Video/Image Processing and Multimedia Communications (EC-VIP-MC 2003), Zagreb, Croatia, July 2003, pp. 181–186 (2003)Google Scholar
  12. 12.
    Kittler, J.: Combining Classifiers: A Theoretical Framework. Pattern Analysis and Application 1, 18–27 (1998)CrossRefGoogle Scholar
  13. 13.
    Yule, G.: On the association of attributes in statistics. Phil. Transaction, A 194, 257–319 (1900)CrossRefGoogle Scholar
  14. 14.
    Sneath, P., Sokal, R.: Numerical Taxonomy. W.H. Freeman and Company, New York (1973)zbMATHGoogle Scholar
  15. 15.
    Giacinto, G., Roli, F.: Design of effective neural network ensembles for image classification processes. Image and Vision Computing 19(9/10), 699–707 (2001)CrossRefGoogle Scholar
  16. 16.
    Cunningham, P., Carney, J.: Diversity versus quality in classification ensembles based on feature selection. In: TCD-CS-200-02, Trinity College Dublin (2000)Google Scholar
  17. 17.
    Dietterich, T.: An experimental comparison of 3 methods for constructing ensembles of decision trees: Bagging, boosting and randomization. Machine Learning 40(2), 139–157 (2000)CrossRefGoogle Scholar
  18. 18.
    Patridge, D., Krazanowski, W.J.: Software Diversity: Practical Statistics for its measurement and exploitation. Inf. and Software Tech. 39, 707–717 (1997)CrossRefGoogle Scholar
  19. 19.
    VisTex, Colour Image Database: VisionTexture (2000), http://www.white.media.mit.edu/vismod/imagery/
  20. 20.
    Texture Library Database, http://textures.forrest.cz
  21. 21.
    Kleinbaum, D.G., Kupper, L.L.: Applied Regression Analysis and other Multivariable methods. Duxberry Press, North Scituate, ISBN 0-87872-139-8Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2005

Authors and Affiliations

  • Samuel Chindaro
    • 1
  • Konstantinos Sirlantzis
    • 1
  • Michael Fairhurst
    • 1
  1. 1.Department of ElectronicsUniversity of KentCanterbury

Personalised recommendations