Classification and clustering perspective towards spectral unmxing
Authors:
- 3 November 2016
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 6145-6148
Abstract
Spectral unmixing techniques decompose the pixels into constituent fractions in order to extract the subpixel information. This study reviews spectral unmixing techniques from a perspective different from earlier approaches in that the problem is studied from a classification as well as clustering perspective. In this research, we focus on addressing some core issues of spectral unmixing such as endmember variability, requirement of pure endmember values, and initialization sensitivity modelling. We propose a Support Vector Machine (SVM) based unmixing technique that incorporates endmember spectral variability. The method uses endmember extraction techniques to give optimal performance even in the absence of training samples. Further, our study presents an alternation of FCM based method for incorporating spectral variability, and the approach is found to be resilient to the brightness variation. An automatic approach for fuzziness parameter selection is also introduced. The sensitivity of FCM towards endmember initialization has been considerably reduced by optimizing the initial seed selection. The proposed approaches have been analyzed over various standard datasets.Keywords
This publication has 9 references indexed in Scilit:
- Comparison of hyperspectral endmember extraction algorithmsJournal of Applied Remote Sensing, 2013
- Probabilistic outputs for twin support vector machinesKnowledge-Based Systems, 2012
- OPTIMISATION OF FUZZY BASED SOFT CLASSIFIERS FOR REMOTE SENSING DATAThe International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2012
- SVM-Based Unmixing-to-Classification Conversion for Hyperspectral Abundance QuantificationIEEE Transactions on Geoscience and Remote Sensing, 2011
- A Novel Technique for Subpixel Image Classification Based on Support Vector MachineIEEE Transactions on Image Processing, 2010
- A note on Platt’s probabilistic outputs for support vector machinesMachine Learning, 2007
- Support vector machine‐based feature selection for land cover classification: a case study with DAIS hyperspectral dataInternational Journal of Remote Sensing, 2006
- AN UNSUPERVISED KERNEL BASED FUZZY C-MEANS CLUSTERING ALGORITHM WITH KERNEL NORMALISATIONInternational Journal of Computational Intelligence and Applications, 2004
- ICE: a statistical approach to identifying endmembers in hyperspectral imagesIEEE Transactions on Geoscience and Remote Sensing, 2004