Abstract
This paper is concerned with the comparison of three types of Gaussian based Artificial Neural Networks in the very high dimensionality classification problems found in hyperspectral signal processing. In particular, they have been compared for the spectral unmixing problem given the fact that the requirements for this type of classification are very different from other realms in two aspects: there are usually very few training samples leading to networks that are very easily overtrained, and these samples are not usually representative in terms of sampling the whole input-output space. The networks selected for comparison go from the classical Radial Basis Function (RBF) network to the more complex Gaussian Synapse Based Network (GSBN) considering an intermediate type, the Radial Basis Function with Multiple Deviation (RBFMD). The comparisons were carried out when processing a benchmark set of synthetic hyperspectral images containing mixtures of spectra from materials found in the US Geological Service database.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Fingas, M.F., Brown, C.E.: Review of Oil Spill Remote Sensing. In: Proceedings of the Fifth International Conference on Remote Sensing for Marine and Coastal Environments, Environmental Research Institute of Michigan, Ann Arbor, Michigan, pp. I211–I218 (2000)
Regional Marine Pollution Emergency Response Centre for the Mediterranean Sea (REMPEC): MEDIPOL 2003 - European workshop on satellite imagery and illicit oil spills in Europe and in the Mediterranean. Final Recommendations (2003)
Bissett, W.P., Arnone, R., Davis, C.O., Dickey, T., Dye, D.R., Kohler, D.D.R., Gould, R.: From meters to kilometers - a look at ocean color scales of variability, spatial coherence, and the need for fine scale remote sensing in coastal ocean optics. Oceanography (2003)
Campbell, J.: Introduction to Remote Sensing. The Guilford Press, New York (1996)
Hsu, P.H., Tseng, C.E.: Feature Extraction for Hyperspectral Image. In: Proceedings of the 20th Asian Conference on Remote Sensing, vol. 1, pp. 405–410 (1999)
Merényi, E., Minor, T.B., Taranik, J.V., Farrand, W.H.: Quantitative Comparison of Neural Network and Conventional Classifiers for Hyperspectral Imagery. In: GreeN, R.O. (ed.) Summaries of the Sixth Annual JPL Airborne Earth Science Workshop, AVIRIS Workshop, Pasadena, CA, March 4-8, vol. 1 (1996)
Ghosh, J.: Adaptive and neural methods for image segmentation. In: Bovik, A. (ed.) Handbook of Image and Video Processing, ch. 4.10, pp. 401–414. Academic Press, London (2000)
Tadjudin, S., Landgrebe, D.: Covariance Estimation with Limited Training Samples. IEEE Trans. Geos. Rem. Sensing 37(4), 2113–2118 (1999)
Tadjudin, S., LandgrebeRobust, D.: Parameter estimation for mixture model. IEEE Trans. Geos. Rem. Sensing 38(1), 439 (2000)
Murat Dundar, M.: David Landgrebe: Toward an Optimal Supervised Classifier for the Analysis of Hyperspectral Data. IEEE Transactions on Geoscience and Remote Sensing 42(1), 271–277 (2004)
Crespo, J.L., Duro, R.J., López Peña, F.: Unmixing Low Ratio Endmembers through Gaussian Synapse ANNs in Hyperspectral Images. In: Proceedings CIMSA 2004 IEEE International Symposium on Computational Intelligence for Measurement Systems and Applications, vol. V1, pp. 150–154 (2003)
Duro, R.J., Crespo, J.L., Santos, J.: Training Higher Order Gaussian Synapses. In: Mira, J. (ed.) IWANN 1999. LNCS, vol. 1606, pp. 537–545. Springer, Heidelberg (1999)
Karayiannis, N.B.: Reformulated radial basis neural networks trained by gradient descent. IEEE Transactions on Neural Networks 10(3), 657–671 (1999)
Graña, M., Raducanu, B., Sussner, P., Ritter, G.: On Endmember Detection in Hyper- spectral Images with Morphological Associative Memories. In: Presented at IBERAMIA 2002, Sevilla, Spain, pp. 526-535 (2002)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Prieto, A., Bellas, F., Duro, R.J., Lopez-Peña, F. (2005). A Comparison of Gaussian Based ANNs for the Classification of Multidimensional Hyperspectral Signals. In: Cabestany, J., Prieto, A., Sandoval, F. (eds) Computational Intelligence and Bioinspired Systems. IWANN 2005. Lecture Notes in Computer Science, vol 3512. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11494669_101
Download citation
DOI: https://doi.org/10.1007/11494669_101
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-26208-4
Online ISBN: 978-3-540-32106-4
eBook Packages: Computer ScienceComputer Science (R0)