SAR Image Classification Based on Clonal Selection Algorithm

  • Wenping Ma
  • Ronghua Shang
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4221)


This paper presents a new classification method based on the Clonal Selection Principle, named Clonal Selection Algorithm (CSA). The new algorithm can carry out the global search and the local search in many directions rather than one direction around the same antibody simultaneously, and obtain the global optimum quickly. The implementation of new algorithm composes of three main processes: firstly, selecting training samples and choosing clustering centers randomly. Secondly, training samples using CSA, and obtaining optimal clustering center based on three main clonal operations: cloning, clonal mutation and clonal selection. Finally, output the classification results according to clustering center obtained. To show the usefulness of this approach, experiment with simulated SAR image was considered. The classification results are evaluated by comparing with three well-known algorithms, UAIC, K-means, and fuzzy K-means. Accroding to the overall accuracy and Kappa coefficient, CSA has high classification precision and can be used in SAR images classification.


Cluster Center Synthetic Aperture Radar Clonal Selection Synthetic Aperture Radar Image Artificial Immune 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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Burnet, F.M.: The Clonal Selection Theory of Acquired Immunity, p. 15. Cambridge University Press, Cambridge (1959); Burnet, F.M. Clonal selection and after. Theoretical Immunology, pp. 63–85. Marcel Dekker, New York (1978)Google Scholar
  2. 2.
    De Castro, L.N., Von Zuben, F.J.: The Clonal Selection Algorithm with Engineering Applications. In: Proc. of GECCO 2000, Workshop on Artificial Immune Systems and Their Applications, pp. 36–37 (2000)Google Scholar
  3. 3.
    Kim, J., Bentley, P.: Toward an artificial immune system for network intrusion detection: An investigation of clonal selection with a negative selection operator. In: Proc. Congress on Evolutionary Computation (CEC), Seoul, Korea, vol. 2, pp. 1244–1252 (2001)Google Scholar
  4. 4.
    Du, H., Jiao, L., Wang, S.: Clonal Operator and Antibody Clone Algorithms. In: Proceedings of the First International Conference on Machine Learning and Cybernetics, Beijing, pp. 506–510 (2002)Google Scholar
  5. 5.
    Frery, A.C., Mueler, H.J., Yanasse, C.C.F., Sant’ana, S.J.S.: A model for extremely heterogeneous clutter. IEEE Transactions on Geoscience and Remote Sensing 35(3), 648–659 (1997)CrossRefGoogle Scholar
  6. 6.
    Hofmeyr, S.A., Forrest, S.: Immunity by design: An artificial immune system. In: Proc. Genetic and Evolutionary Computation Conf (GECCO), pp. 1289–1296 (1999)Google Scholar
  7. 7.
    Timmis, J., Neal, M., Hunt, J.E.: An artificial immune system for data analysis. Biosystem 55(1/3), 143–150 (2000)CrossRefGoogle Scholar
  8. 8.
    Zhong, Y., Zhang, L., Huang, B., Li, P.: An Unsupervised Artificial Immune Classifier for Multi/Hyperspectral Remote Sensing Imagery. IEEE Transactions on Geoscience and Remote Sensing 44(2), 420–431 (2006)CrossRefGoogle Scholar
  9. 9.
    Hall, D., Ball, G.: Isodata: A novel method of data analysis and pattern classification, Stanford Res. Inst., Stanford, CA, Tech. Rep. (1965)Google Scholar
  10. 10.
    Thitimajshima, P.: A new modified fuzzy c-means algorithm for multispectral satellite images segmentation. In: Proc. IGARSS, vol. 4, pp. 1684–1686 (2000)Google Scholar
  11. 11.
    Guangyan, Z.: Principles of Immunology. Shang Hai Technology Literature Publishing Company (2000) (in Chinese) Google Scholar
  12. 12.
    Dasgupta, D., Forrest, S.: Artificial immune systems in industrial applications. In: Proceedings of the Second International Conference on Intelligent Processing and Manufacturing of Materials, pp. 257–267. IEEE press, Los Alamitos (1999)CrossRefGoogle Scholar
  13. 13.
    de Castro, L.N.: Larning and Optimization Using the Clonal Slection Principle. IEEE Transactions on Evolutionary Computation 6(3), 239–251 (2002)CrossRefGoogle Scholar
  14. 14.
    Food, G.M.: Status of Land Cover Classification Accuracy Assessment[A]. Remote Sensing of Environment 80, 185–201 (2002)CrossRefGoogle Scholar
  15. 15.
    Jiao, L., Wang, L.: A novel genetic algorithm based on immunity. IEEE Transactions on Systems, Man and Cybernetics, Part A 30(5) (September 2000)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Wenping Ma
    • 1
  • Ronghua Shang
    • 1
  1. 1.Institute of Intelligent Information ProcessingXidian UniversityXi’anP.R. China

Personalised recommendations