Abstract
Although hyperspectral imagery provides abundant information about bands, their high dimensionality also substantially increases the computational burden. An interesting task in hyperspectral data processing is to reduce the redundancy of the spectral and spatial information without loss of any valuable details. In this paper, a band selection technique with principal components analysis, maxima-minima functional, and information gain for hyperspectral imagery such as small multi-mission satellite imagery is presented. Band selection method in the present research does not only serve as the first step of hyperspectral data processing that leads to a significant reduction of computational complexity but also an invaluable research tool to identify optimal spectral for different satellite applications. In this paper, an integrated PCA, maxima-minima functional method and information gain is proposed for hyperspectral band selection. Based on tests in SMMS hyperspectral imagery, this new method achieves good result in terms of robust clustering.
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
Richards, J.A.: Remote Sensing Digital Image Analysis: An introduction. Springer, Heidelberg (1986)
Small Multi-Mission Satellite (SMMS) Data Available, http://smms.ee.ku.ac.th/index.php
Agarwal, A., El-Ghazawi, T., El-Askary, H., Le-Moigne, J.: Efficient Hierarchical-PCA Dimension Reduction for Hyperspectral Imagery. In: 2007 IEEE International Symposium on Signal Processing and Information Technology, December 15-18, pp. 353–356 (2007)
Kaewpijit, S., Le-Moige, J., El-Ghazawi, T.: Hyperspectral Imagery Dimension Reduction Using Pricipal Component Analysis on the HIVE. In: Science Data Processing Workshop. NASA Goddard Space Flight Center (February 2002)
Koonsanit, K., Jaruskulchai, C.: Band Selection for Hyperspectral Image Using Principal Components Analysis and Maxima-Minima Functional. In: Theeramunkong, T., Kunifuji, S., Sornlertlamvanich, V., Nattee, C. (eds.) KICSS 2010. LNCS, vol. 6746, pp. 103–112. Springer, Heidelberg (2011)
Cheng, X., Chen, Y.R., Tao, Y., Wang, C.Y., Kim, M.S., Lefcourt, A.M.: A novel integrated PCA and FLD method on hyperspectral image feature extraction for cucumber chilling damage inspection. ASAE Transactions 47(4), 1313–1320 (2004)
Kirkby, R., Frank, E.: Weka Explorer User Guide. University of Waikato, New Zealand (2005)
Frank, A., Asuncion, A.: UCI Machine Learning Repository. University of California, School of Information and Computer Science, Irvine, CA (2010), http://archive.ics.uci.edu/ml/support/Statlog
Zhao, Z., et al.: Advancing Feature Selection Research, http://featureselection.asu.edu/featureselection_techreport.pdf (retrieved: September 2, 2010)
Jackson, J.E.: A User Guide to Principal Components. John Wiley and Sons, New York (1991)
Jolliffe, I.T.: Principal Component Analysis. Springer (1986)
Cover, T.M., Thomas, J.A.: Information Gain. In: Elements of Information Theory. Wiley (1991)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Koonsanit, K., Jaruskulchai, C., Eiumnoh, A. (2012). Band Selection for Hyperspectral Imagery with PCA-MIG. In: Bao, Z., et al. Web-Age Information Management. WAIM 2012. Lecture Notes in Computer Science, vol 7419. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-33050-6_13
Download citation
DOI: https://doi.org/10.1007/978-3-642-33050-6_13
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-33049-0
Online ISBN: 978-3-642-33050-6
eBook Packages: Computer ScienceComputer Science (R0)