Hyperspectral Image Analysis Based on Color Channels and Ensemble Classifier

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8480)


Hyperspectral image analysis is a dynamically developing branch of computer vision due to the numerous practical applications and high complexity of data. There exist a need for introducing novel machine learning methods, that can tackle high dimensionality and large number of classes in these images. In this paper, we introduce a novel ensemble method for classification of hyperspectral data. The pool of classifiers is built on the basis of color decomposition of the given image. Each base classifier corresponds to a single color channel that is extracted. We propose a new method for decomposing hyperspectral image into 11 different color channels. As not all of the channels may bear as useful information as other, we need to promote the most relevant ones. For this, our ensemble uses a weighted trained fuser, which uses a neural methods for establishing weights. We show, that the proposed ensemble can outperform other state-of-the-art classifiers in the given task.


machine learning classifier ensemble multiple classifier system hyperspectral image image segmentation color channels 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Agarwal, A., El-Ghazawi, T., El-Askary, H., Le-Moigne, J.: Efficient hierarchical-PCA dimension reduction for hyperspectral imagery. In: 2007 IEEE International Symposium on Signal Processing and Information Technology, pp. 353–356 (December 2007)Google Scholar
  2. 2.
    Alpaydin, E.: Combined 5 x 2 cv f test for comparing supervised classification learning algorithms. Neural Computation 11(8), 1885–1892 (1999)CrossRefGoogle Scholar
  3. 3.
    Cyganek, B.: One-class support vector ensembles for image segmentation and classification. Journal of Mathematical Imaging and Vision 42(2-3), 103–117 (2012)CrossRefzbMATHMathSciNetGoogle Scholar
  4. 4.
    Dai, Q.: A competitive ensemble pruning approach based on cross-validation technique. Knowledge-Based Systems 37, 394–414 (2013)CrossRefGoogle Scholar
  5. 5.
    Davies, E.R.: Machine Vision: Theory, Algorithms, Practicalities. Elsevier (December 2004)Google Scholar
  6. 6.
    Durand, J.M., Kerr, Y.H.: An improved decorrelation method for the efficient display of multispectral data. IEEE Transactions on Geoscience and Remote Sensing 27(5), 611–619 (1989)CrossRefGoogle Scholar
  7. 7.
    Jain, A.K., Duin, R.P.W., Mao, J.: Statistical pattern recognition: a review. IEEE Transactions on Pattern Analysis and Machine Intelligence 22(1), 4–37 (2000)CrossRefGoogle Scholar
  8. 8.
    Krawczyk, B., Woźniak, M., Cyganek, B.: Clustering-based ensembles for one-class classification. Inf. Sci. 264, 182–195 (2014)CrossRefGoogle Scholar
  9. 9.
    Kuncheva, L.I., Jain, L.C.: Designing classifier fusion systems by genetic algorithms. IEEE Transactions on Evolutionary Computation 4(4), 327–336 (2000)CrossRefGoogle Scholar
  10. 10.
    Szczurek, A., Krawczyk, B., Maciejewska, M.: Vocs classification based on the committee of classifiers coupled with single sensor signals. Chemometrics and Intelligent Laboratory Systems 125, 1–10 (2013)CrossRefGoogle Scholar
  11. 11.
    Tamai, S.: Image processing suitable for changing the number of colors in an image, U.S. Classification: 358/518; 358/501; 358/520; 358/530 International Classification: G03F 308 (September 1999)Google Scholar
  12. 12.
    Tyo, J.S., Konsolakis, A., Diersen, D.I., Olsen, R.C.: Principal-components-based display strategy for spectral imagery. IEEE Transactions on Geoscience and Remote Sensing 41(3), 708–718 (2003)CrossRefGoogle Scholar
  13. 13.
    van Erp, M., Vuurpijl, L., Schomaker, L.: An overview and comparison of voting methods for pattern recognition. In: Proceedings. Eighth International Workshop on Frontiers in Handwriting Recognition 2002, pp. 195–200 (2002)Google Scholar
  14. 14.
    Woźniak, M., Graña, M., Corchado, E.: A survey of multiple classifier systems as hybrid systems. Information Fusion 16, 3–17 (2014)CrossRefGoogle Scholar
  15. 15.
    Woźniak, M., Zmyslony, M.: Designing combining classifier with trained fuser - analytical and experimental evaluation. Neural Network World 20(7), 925–934 (2010)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  1. 1.Department of Systems and Computer NetworksWrocław University of TechnologyWrocławPoland

Personalised recommendations