Optimal Hierarchical Remote Sensing Image Clustering Using Imperialist Competitive Algorithm

  • Samaneh Karami
  • Shahriar Baradaran Shokouhi
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 124)


In this paper a novel technique is proposed for automated hierarchical clustering of remote sensing images. Traditionally, in an unsupervised clustering the number of clusters needs to be fixed and usually the RGB values of pixels are used to compute similarity measure for assigning them to specific classes. The proposed algorithm is basically a two-phase process. At the first phase the original data set is decomposed into water and land cover classes using near Infrared band’s information. At the second phase Imperialist Competitive Algorithm is used to determine the number and centers of land cover clusters using RGB information. The optimization is based on K-Means and an additional term for improving the accuracy of clustering. The method is applied on 2 artificial data sets and an IKONOS image of a part of city Tehran. Results obtained from applying this method for both artificial data sets and RS images, indicate promising ability of this method in clustering of images.


Land Cover Cluster Center Competitive Algorithm Imperialist Competitive Algorithm Image Cluster 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Jain, A.K., Duin, P., Jianchang, M.: Statical pattern recognition:a review. IEEE Trans. Patt. Anal. Machine Intell. 22(1), 4–37 (2000)CrossRefGoogle Scholar
  2. 2.
    Zhang, J., Foody, G.M.: Full fuzzy supervised classification of sub-urban land cover from remotely sensed imagery. International Journal of Remote sensing 22, 615–628 (2001)CrossRefGoogle Scholar
  3. 3.
    Garai, G., Chaudhuri, B.B.: A novel genetic algorithm for automatic clustering. Pattern Recognition 25, 173–187 (2004)CrossRefGoogle Scholar
  4. 4.
    Atashpaz-Gargari, E., Lucas, C.: Imperialist Competitive Algorithm: An algorithm for optimization inspired by imperialistic competition. In: IEEE Congress on Evolutionary Computation, Singapore (2007)Google Scholar
  5. 5.
    Atashpaz-Gargari, E., Hashemzadeh, F., Lucas, C.: Evolutionary Design of PID Controller for a MIMO Distillation Column using Colonial Competitive Algorithm. Journal of Intellegent Computing and Cybernetics 1(3), 337–355 (2008)CrossRefMathSciNetGoogle Scholar
  6. 6.
    Biabangard-Oskouyi, E., Atashpaz-Gargari, N., Soltani, N., Lucas, C.: Application of Imperialist Competitive Algorithm for materials property characterization from sharp indentation test. International Journal of Engineering Simulation (2008)Google Scholar
  7. 7.
    Khhabbazi, A., Atashpaz, E., Lucas, C.: Imperialist competitive algorithm for minimum bit error rate beamforming. Internatilonal Journal of Bio-Inspired Computation 1, 125–133 (2009)CrossRefGoogle Scholar
  8. 8.
    Rajabioun, R., Atashpaz-Gargari, E., Lucas, C.: Colonial Competitive Algorithm as a Tool for Nash Equilibrium Point Achievement. In: Gervasi, O., Murgante, B., Laganà, A., Taniar, D., Mun, Y., Gavrilova, M.L. (eds.) ICCSA 2008, Part II. LNCS, vol. 5073, pp. 680–695. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  9. 9.
    Wolf, P.R., Dewitt, B.A.: Elements of photogrammetry applications in GIS, 3rd edn. McGrow-Hill, NY (2000)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Samaneh Karami
    • 1
  • Shahriar Baradaran Shokouhi
    • 1
  1. 1.Iran University of Science and TechnologyTehranIran

Personalised recommendations