An Application of Neural and Probabilistic Unsupervised Methods to Environmental Factor Analysis of Multi-spectral Images

  • Luca Pugliese
  • Silvia Scarpetta
  • Anna Esposito
  • Maria Marinaro
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3617)


In this paper we test the performance of two unsupervised clustering strategies for the analysis of LANDSAT multispectral images of the Temples of Paestum Area in Italy. The classification goal is to identify environmental factors (soils, vegetation types, water) on the images, exploiting the features of the seven LANDSAT spectral bands. The first strategy is a fast migrating means technique based on a Maximum Likelihood Principle (ISOCLUST algorithm),and the second is the Kohonen Self Organizing Map (SOM) neural network. The advantage of using the SOM algorithm is that both the information on classes and the similarity between the classes are obtained (since proximity corresponds to similarity among neurons). By exploiting the information on class similarity it was possible to automatically colour each cluster identified by the net (assigning a specific colour to each of them) thus facilitating a successive photo-interpretation.


  1. 1.
    Fu, K.S., Landgrebe, D.A., Phillips, T.L.: Information Processing of Remotely Sensed Agricultural Data. Proceeding of IEEE 57, 639–653 (1969)CrossRefGoogle Scholar
  2. 2.
    Goldberg, M., Shlien, S.: A Clustering Scheme for Multispectral Images. IEEE Trans. SMC 8, 86–92 (1978)Google Scholar
  3. 3.
    Benediktsson, J., Philip, H.S., Okan, K.E.: Neural Network Approaches Versus Statistical Methods in Classification of Multi-source Remote Sensing Data. IEEE Transactions on Geoscience and Remote Sensing 28(4), 540–551 (1990)CrossRefGoogle Scholar
  4. 4.
    McClelland, G.E., Dewitt, R.N., Hemmer, T.H., Matheson, L.N., Moe, G.O.: Multispectral Image-Processing with Three-Layer Back-Propagation Network. In: Proceedings of the International Joint Conference on Neural Networks, vol. 1, pp. 151–153. I.E.E.E, New York (1989)CrossRefGoogle Scholar
  5. 5.
    Kamata, S., Kawaguchi, E.: A Neural Classifier for Multi-Temporal Landsat Images Using Spatial and Spectral Information. In: Proceedings of International Joint Conference on Neural Networks, Nagoya, Japan, pp. 2199–2202 (1993)Google Scholar
  6. 6.
    Wang, Y., Jamshidi, M., Neville, P., Bales, C., Morain, S.: Multispectral Landsat Image Classification Using a Data Clustering Algorithm. In: Proceedings of 3th Intenational Conference on Machine Learning and Cybernetics, Shangai, pp. 4380–4384 (2004)Google Scholar
  7. 7.
    Vassilas, N., Charou, E.: A New Methodology for Efficient Classification of Multispectral Satellite Images Using Neural Networks Techniques. Neural Processing Letters 9, 35–43 (1999)CrossRefGoogle Scholar
  8. 8.
    Richards, J.A., Jia, X.: Remote Sensing Digital Image Analysis, pp. 58–59, 225, 235–236. Springer, Heidelberg (1999)Google Scholar
  9. 9.
    Chavez Jr., P.S.: Image-Based Atmospheric Corrections Revisited and Revised. Photogrammetric Engineering and Remote Sensing 62(9), 1025–1036 (1996)Google Scholar
  10. 10.
    Kohonen, T.: Self-Organizing Maps, 2nd edn. Series in Information Sciences, vol. 30. Springer, Heidelberg (1997)zbMATHGoogle Scholar
  11. 11.
    Mather, P.M.: Computer Processing of Remotely Sensed Images an Introduction, 2nd edn. John Wiley Press, Chichester (1999)Google Scholar
  12. 12.
    Büttner, G., et al.: The European Corine Land Cover Project. In: XXth Congress of International Society for Photogrammetry and Remote Sensing, Istanbul, Turkey (2004)Google Scholar
  13. 13.
    Borg, I., Groenen, P.: Modern Multidimensional Scaling. Springer, New York (1997)zbMATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2005

Authors and Affiliations

  • Luca Pugliese
    • 1
  • Silvia Scarpetta
    • 3
    • 4
  • Anna Esposito
    • 1
    • 2
  • Maria Marinaro
    • 1
    • 3
    • 4
  1. 1.IIASS, Istituto Internazionale per gli Alti Studi Scientifici "E.R.Caianiello"Vietri sul Mare – Salerno
  2. 2.Dipartimento di PsicologiaSeconda Università di NapoliCaserta
  3. 3.Dipartimento di Fisica "E.R.Caianiello"Università degli Studi di SalernoSalernoItaly
  4. 4.INFM and INFN Sezione di SalernoItaly

Personalised recommendations