IMPROVEMENT OF DIFFERENTIAL CRISP CLUSTERING USING ANN CLASSIFIER FOR UNSUPERVISED PIXEL CLASSIFICATION OF SATELLITE IMAGE

Indrajit Saha, Dariusz Plewczynski, Ujjwal Maulik, Sanghamitra Bandyopadhyay

2010

Abstract

An important approach to unsupervised pixel classification in remote sensing satellite imagery is to use clustering in the spectral domain. In particular, satellite images contain landcover types some of which cover significantly large areas, while some (e.g., bridges and roads) occupy relatively much smaller regions. Detecting regions or clusters of such widely varying sizes presents a challenging task. This fact motivated us to present a novel approach that integrates a differential evaluation based crisp clustering scheme with artificial neural networks (ANN) based probabilistic classifier to yield better performance. Real-coded encoding of the cluster centres is used for the differential evaluation based crisp clustering. The clustered solution is then used to find some points based on their proximity to the respective centres. The ANN classifier is thereafter trained by these points. Finally, the remaining points are classified using the trained classifier. Results demonstrating the effectiveness of the proposed technique are provided for several synthetic and real life data sets. Also statistical significance test has been performed to establish the superiority of the proposed technique. Moreover, one remotely sensed image of Bombay city has been classified using the proposed technique to establish its utility.

References

  1. (1986). IRS data users handbook. NRSA, Hyderabad, India.
  2. Andersen, L. N., Larsen, J., Hansen, L. K., and HintzMadsen, M. (1997). Adaptive regularization of neural classifiers. In. Proc. of the IEEE workshop on neural networks for signal processing VII, NewYork, USA, pages 24-33.
  3. Bishop, C. (1996). Neural Networks for Pattern Recognition. Oxford University Press.
  4. Everitt, B. S. (1993). Cluster Analysis. Halsted Press, Third edition.
  5. Goldberg, D. E. (1989). Genetic Algorithms in Search, Optimization and Machine Learning. Addison-Wesley, New York.
  6. Hollander, M. and Wolfe, D. A. (1999). Nonparametric Statistical Methods. 2nd ed.
  7. Jain, A. K. and Dubes, R. C. (1988). Algorithms for Clustering Data. Prentice-Hall, Englewood Cliffs, NJ.
  8. Jain, A. K., Murty, M. N., and Flynn, P. J. (1999). Data clustering: A review, volume 31.
  9. Jardine, N. and Sibson, R. (1971). Mathematical Taxonomy. John Wiley and Sons.
  10. Kirkpatrik, S., Gelatt, C. D., and Vecchi, M. P. (1983). Optimization by simulated annealing. Science, 220:671- 680.
  11. Laprade, R. H. (1988). Split-and-merge segmentation of aerial photographs. Computer Vision Graphics and Image Processing, 48:77-86.
  12. MacKay, D. J. C. (1992). The evidence framework applied to classification networks. Neural Computation, 4:720-736.
  13. Maulik, U. and Bandyopadhyay, S. (2002). Performance evaluation of some clustering algorithms and validity indices. IEEE Transactions on Pattern Analysis and Machine Intelligence, 24(12):1650-1654.
  14. Sigurdsson, S., Larsen, J., and Hansen, L. (2002). Outlier estimation and detection: application to skin lesion classification. In Proc. Int. conf. on acoustics, speech and signal processing.
  15. Storn, R. and Price, K. (1995). Differential evolution - A simple and efficient adaptive scheme for global optimization over continuous spaces. Technical Report TR-95-012, International Computer Science Institute, Berkley (1995).
  16. Storn, R. and Price, K. (1997). Differential evolution - A simple and efficient heuristic strategy for global optimization over continuous spaces. Journal of Global Optimization, 11:341-359.
  17. van Laarhoven, P. J. M. and Aarts, E. H. L. (1987). Simulated Annealing: Theory and Applications. Kluwer Academic Publisher.
  18. Wong, Y. F. and Posner, E. C. (1993). A new clustering algorithm applicable to polarimetric and sar images. IEEE Transactions on Geoscience and Remote Sensing, 31(3):634-644.
Download


Paper Citation


in Harvard Style

Saha I., Plewczynski D., Maulik U. and Bandyopadhyay S. (2010). IMPROVEMENT OF DIFFERENTIAL CRISP CLUSTERING USING ANN CLASSIFIER FOR UNSUPERVISED PIXEL CLASSIFICATION OF SATELLITE IMAGE . In Proceedings of the 12th International Conference on Enterprise Information Systems - Volume 2: ICEIS, ISBN 978-989-8425-05-8, pages 21-29. DOI: 10.5220/0002872800210029


in Bibtex Style

@conference{iceis10,
author={Indrajit Saha and Dariusz Plewczynski and Ujjwal Maulik and Sanghamitra Bandyopadhyay},
title={IMPROVEMENT OF DIFFERENTIAL CRISP CLUSTERING USING ANN CLASSIFIER FOR UNSUPERVISED PIXEL CLASSIFICATION OF SATELLITE IMAGE},
booktitle={Proceedings of the 12th International Conference on Enterprise Information Systems - Volume 2: ICEIS,},
year={2010},
pages={21-29},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0002872800210029},
isbn={978-989-8425-05-8},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 12th International Conference on Enterprise Information Systems - Volume 2: ICEIS,
TI - IMPROVEMENT OF DIFFERENTIAL CRISP CLUSTERING USING ANN CLASSIFIER FOR UNSUPERVISED PIXEL CLASSIFICATION OF SATELLITE IMAGE
SN - 978-989-8425-05-8
AU - Saha I.
AU - Plewczynski D.
AU - Maulik U.
AU - Bandyopadhyay S.
PY - 2010
SP - 21
EP - 29
DO - 10.5220/0002872800210029