Abstract
In this work we have made use of a new type of network with non linear synapses, Gaussian Synapse Networks, for the segmentation of hyperspectral images. These structures were trained using the GSBP algorithm and present two main advantages with respect to other, more traditional, approaches. On one hand, through the intrinsic filtering ability of the synapses, they permit concentrating on what is relevant in the spectra and automatically discard what is not. On the other, the networks are structurally adapted to the problem as superfluous synapses and/or nodes are implicitly eliminated by the training procedure.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Staenz, K., Canadian Activities in Terrestrial Imaging Spectrometry. 994 Annual Report, Canada Centre for Remote Sensing. (1995) 68.
Wiemker R., Speck A., Kulbach D., Spitzer H., Bienlein J., Unsupervised Robust Change Detection on Multispectral Imagery Using Spectral and Spatial Features. Proceedings of the Third International Airborne Remote Sensing Conference and Exhibition, Copenhagen, vol. I, ERIM, Ann Arbor (1997) 640–647.
Gao, B-C., and Goetz, A.F.H. Column Atmospheric Water Vapor and Vegetation Liquid Water Retrievals From Airborne Imaging Spectrometer Data, J. Geophys. Res., 95, (1990) 3549–3564.
Vane, G. T., First Results of the Airborne Visible/Infrared Imaging Spectrometer (AVIRIS), SPIE, Vol 834 Imaging Spectroscopy, (1987) 166–174.
Rencz A. (Editor). Manual of Remote Sensing. John Wiley and Sons, Inc. New York, 1999.
Hsu, P.H. and Tseng, Y.H. Feature Extraction for Hyperspectral Image. Proceedings of the 20th Asian Conference on Remote Sensing, Vol. 1, (1999) 405–410.
Schowengerdt, R.A.. Remote Sensing: Models and Methods for Image Processing, Academic Press. (1997).
Tadjudin, S. and Landgrebe, D. Classification of High Dimensional Data with Limited Training Samples. PhD Thesis and School of Electrical & Computer Engineering Technical Report TR-ECE 98-8, Purdue University. (1998).
Lee, C. and Landgrebe, D. Feature Extraction and Classification Algorithms for High Dimensional Data. TR-EE 93-1, Purdue University. (1993).
Duro, R.J., Crespo, J.L., and Santos, J.: Training Higher Order Gaussian Synapses. LNCS, Vol. 1606 Springer-Verlag, Berlín (1999) 537–545.
Landgrebe, D. Indian Pines AVIRIS Hyperspectral Reflectance Data: 92av3c. available at http://makalu.jpl.nasa.gov/locator/index.html. (1992).
Tadjudin, S. and Landgrebe, D. Covariance Estimation for Limited Training Samples. Int. Geoscience and Remote Sensing Symp. Seattle, (1998).
Guatieri, J.A., Bechdol, M., Chettri, S., Robinson, J.W., Garegnani, J., Vermeulen, A. and Antonille, S. From Spectra to Cassification. Extended paper of the presentation at 1st International Symposium on Hyperspectral Analysis, Caceres, Spain. (2000).
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2002 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Crespo, J.L., Duro, R.J., López-Peña, F. (2002). Gaussian Synapse Networks for Hyperspectral Image Segmentation. In: Garijo, F.J., Riquelme, J.C., Toro, M. (eds) Advances in Artificial Intelligence — IBERAMIA 2002. IBERAMIA 2002. Lecture Notes in Computer Science(), vol 2527. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-36131-6_51
Download citation
DOI: https://doi.org/10.1007/3-540-36131-6_51
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-00131-7
Online ISBN: 978-3-540-36131-2
eBook Packages: Springer Book Archive