The Band Selection Algorithm in Supervised Classification Using Mixed-Pixels and Canonical Correlation Analysis

  • Hoon Chang
  • Hwan-Hee Yoo
  • Hong Sok Kim
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3984)


The commonly used methods for the optimum band selection in supervised classification of multi-spectral data are Divergence, Transformed divergence (TD) and Jeffreys-Matusita distance (JM distance). But those methods might be ineffective when there is a need to change in the number of bands used and some spectral information in multi-spectral data can be redundant in classification process. This study introduces new algorithm with “bands variables set” and “classes variables set”, the canonical correlation analysis is made use of feature classification. Using the canonical cross-loadings we can orderly identify the bands correlation that largely affects the remotely sensed data. To verify the suitability of the new algorithm, the classifications using the each best band combination through TD, JM distance and new method were performed and the accuracy was assesed. As a result of classification accuracy assessment, overall accuracy and k^ for the new method were superior to TD’s and had competitive results to JM distance method.


Canonical Correlation Analysis Spectral Information Bare Land Supervise Classification Band Selection 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Bartlett, M.S.: The Goodness of Fit of a Single Hypothetical Discriminant Function in the Case of Several Groups. Annals of Eugenics, 199–216 (1951)Google Scholar
  2. 2.
    Dean, M.E., Hoffer, R.M.: Feature Selection Methodologies using Simulated Thematic Mapper Data. In: Symposium on Machine Processing of Remote Sensed Data, LARS, Purdue University, West Lafayette, Indiana, pp. 347–356 (1983)Google Scholar
  3. 3.
    Fitzpatrick-Lins, K.: Comparison of Sampling Procedures and Data Analysis for a Land-use and Land-cover Map. Photogrammetric Engineering and Remote Sensing 47, 343–351 (1981)Google Scholar
  4. 4.
    Johnson, R.A., Wichern, D.W.: Applied Multivariate Statistical Analysis. Prentice Hall, London (1998)Google Scholar
  5. 5.
    Krishnapuram, R., Keller, J.: The Possibilistic C-Means Algorithm: Insights and Recognitions. IEEE Trans. Fuzzy System 4, 385–393 (1996)CrossRefGoogle Scholar
  6. 6.
    Lindeman, R.H., Merenda, P.F., Gold, R.Z.: Introduction to Bivariate and Multivariate Analysis, Scott, Foreman and Company, London (1980)Google Scholar
  7. 7.
    Mardia, K.V., Kent, J.T., Bibby, J.M.: Multivariate Analysis. London Academic Press, London (1979)MATHGoogle Scholar
  8. 8.
    Marsh, S.E., Walsh, J.L., Sobrevila, C.: Evaluation of Airborne Video Data for Land-cover Classification Accuracy Assessment in an Isolated Brazilian Forest. Remote Sensing of Environment 48, 61–69 (1994)CrossRefGoogle Scholar
  9. 9.
    Mausel, P.W., Kamber, W.J., Lee, J.K.: Optimum Band Selection for Supervised Classification of Multispectral Data. Photogrammetric Engineering and Remote Sensing 56(1), 55–60 (1990)Google Scholar
  10. 10.
    Swain, P.H., King, R.C.: Two Effective Feature Selection Criteria for Multispectral Remote Sensing. In: Proc. First Int. Joint Conference on Pattern Recognition, pp. 536–540. IEEE, Los Alamitos (1973)Google Scholar
  11. 11.
    Swain, P.H., Davis, M.: Reote Sensing: The Quantitative Approach, pp. 166–174. McGraw-Hill, New York (1978)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Hoon Chang
    • 1
  • Hwan-Hee Yoo
    • 2
  • Hong Sok Kim
    • 1
  1. 1.Dept. of Urban Planning and EngineeringYonsei UniversitySeoulKorea
  2. 2.Urban Engineering DepartmentGyeongsang National UniversityGyeongnamKorea

Personalised recommendations