Advertisement

Self-Organizing Map for Hyperspectral Image Analysis

  • P. Martinez
  • P. L. Aguilar
  • R. M. Pérez
  • M. Linaje
  • J. C. Preciado
  • A. Plaza
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2085)

Abstract

In this paper we present a neural network methodology used for classifying an hyperspectral image referencied as Indian Pines. The network parameters (learning and neighborhood function) are adjusted using a test battery generated from the image, selecting the values that give the best robutness and discrimination capacity. The availity of ground truth allows us to intriduce a new stadistical measure to quantify the resulting classification accuracy. The results of this methodology show an accuracy of 80% in the classification.

Keywords

Output Layer Confusion Matrix Hyperspectral Image Hyperspectral Data Neighborhood Function 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [1]
    Greeen, R.O., Editor, AVIRIS Earth Science Workshop Proceedings, 1988-2000. Available at http://makalu.jpl.nasa.gov/
  2. [2]
    Ifarraguerri, A.; Chang, C.-I. “Multispectral and Hyperspectral Image Analysis with Convex Cones”. IEEE Trans. Geoscience and Remote Sensing, Vol. 37 Issue 2 Part 1, March 1999, 756–770.CrossRefGoogle Scholar
  3. [3]
    Jimenez, L.O., Morales-Morell, A., Creus, A., “Classification of Hyperdimensional Data Based on Feature and Decision Fusion Approaches Using Projection Pursuit, Majority Voting, and Neural Networks”, IEEE Trans. Geoscience and Remote Sensing, Vol. 37 Issue 3 Part 1, May 1999,. 1360–1366.CrossRefGoogle Scholar
  4. [4]
    Richardson L and Kruse F.A., “Identification and Classification of mixed phytoplankton assemblages using AVIRIS image derived spectra” Summaries of the VIII JPL Airborne Earth Science Workshop. (1999), 339–347Google Scholar
  5. [5]
    Parra L, Spence C., Sadja P, Ziehe A., Müller K-R, “Unmixing Hypersepectral Data”Proc. Advances in Neural Information Processing System 12, Proc. Of the 1999 Conference, MIT Press (1999) 942–948Google Scholar
  6. [6]
    Kohonen, T., Self-Organizing Maps (2nd ed.), Springer Series in Information Science. (1997)Google Scholar
  7. [7]
    Bruske, J and Merényi, E.: “Estimating the Intrinsic Dimensionality of Hyperspectral Images”. Proc. European Symposium on Artificial Neural Network, ESANN’99, Bruges, Belgium, (1999), 105–110.Google Scholar
  8. [8]
    Taudjin S and Landgrebe D., Classification of High Dimensional Data with Limited Training Samples, Doctoral Thesis, School of Elelectrical Engineering and Computer Science, Purdue University. (1998).Google Scholar
  9. [9]
    Martínez P., Pérez R.M., Aguilar P.L., Bachiller, P. and Diaz, P., “A Neuronal Tool for AVIRIS Hyperspectral Unmixing”, Summaries of the VIII JPL Airborne Earth Science Workshop, JPL/NASA, (1999), 281–286.Google Scholar
  10. [10]
    Aguilar, P.L., Pérez, R.M., Martínez, P., Bachiller, P., Merchán, A., “Spectra Evaluation and Recognition in the Mixture Problem Using SOFM Algorithm”, Proc. International Symposium on Engineering of Intelligent Systems, (EIS’98), Vol. 2, (1998), 118–124.Google Scholar
  11. [11]
    Aguilar, P.L., Plaza, A., Martínez, P., Pérez, R.M., “Endmember Extraction by a Self-Organizing Neural Network on Hyperspectral Images”, Proc. International Conference on Automation, Robotics and Computer Vision, Nanyang Technological Institute, Singapore, (2000).Google Scholar
  12. [12]
    Aguilar P.L, Martínez, P., Pérez R.M., Hormigo, A., “Abundance Extractions from AVIRIS Images Using a Self Organizing Neural Network”, Summaries of the IX JPL Airborne Earth Science Workshop, JPL/NASA (2000), 281–286,.Google Scholar
  13. [13]
    Aguilar P.L., “Cuantificación de Firmas Hiperespectrales Usando Mapas Autoorganizativos”, Ph. D. Thesis, Escuela Politécnica, Universidad de Extremadura, (Chapter 5), 2000.Google Scholar
  14. [14]
    Chuvieco E., Elementos de Teledetección Espacial, Ed Rialp (2000)Google Scholar
  15. [15]
    Ultsch, A. and Siemon, H.P., “Kohonen’s Self Organizing Feature Maps for Exploratory Data Analysis”, Proc. ICNN’90 International Neural Network Conference, (1990), 305–308.Google Scholar
  16. [16]
    Antonille, S. and Gualtieri, J.A., “Visualizing Clusters in High-Dimensional Data with a Kohonen Self Organizing Map”. Summaries of the IX JPL Airborne Earth Science Workshop, JPL/NASA (2000) 281–286.Google Scholar
  17. [17]
    Martínez, P, Gualtieri, J.A., Aguilar, P.L., Pérez R, Linaje M, Preciado J.C., Plaza A., “Hyperspectral image classification using self-organizing map”, Summaries of the X JPL Airborne Earth Science Workshop, in press, JPL/NASA, 2001.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2001

Authors and Affiliations

  • P. Martinez
    • 1
  • P. L. Aguilar
    • 1
  • R. M. Pérez
    • 1
  • M. Linaje
    • 1
  • J. C. Preciado
    • 1
  • A. Plaza
    • 1
  1. 1.Departamento de InformáticaUniversidad de Extremadura, Avda. de la Universidad s/nCáceresSPAIN

Personalised recommendations