IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · 2012 · 166 citations · 44 references
ComputingComputer ScienceFeature EngineeringMachine LearningRemote SensingDimension ReductionDimensionality ReductionFeature SelectionImage ClassificationRemote Sensing Image AnalysisRemote Sensing ImageryHyperspectral AnalysisHyperspectral ClassificationHyperspectral Image ClassificationHyperspectral Image ProcessingHyperspectral Imagery AnalysisMaterial ClassificationSpectral Band SelectionWavelet Analysis
The rich information available in hyperspectral imagery has provided significant opportunities for material classification and identification. Due to the problem of the “curse of dimensionality” (called Hughes phenomenon) posed by the high number of spectral channels along with small amounts of labeled training samples, dimensionality reduction is a necessary preprocessing step for hyperspectral data. Generally, in order to improve the classification accuracy, noise bands generated by various sources (primarily the sensor and the atmosphere) are often manually removed in advance. However, the removal of these bands may discard some important discriminative information, eventually degrading the classification accuracy. In this paper, we propose a new strategy to automatically select bands without manual band removal. Firstly, wavelet shrinkage is applied to denoise the spatial images of the whole data cube. Then affinity propagation, which is a recently proposed feature selection approach, is used to choose representative bands from the noise-reduced data. Experimental results on three real hyperspectral data collected by two different sensors demonstrate that the bands selected by our approach on the whole data (containing noise bands) could achieve higher overall classification accuracies than those by other state-of-the-art feature selection techniques on the manual-band-removal (MBR) data, even better than the bands identified by the proposed approach on the MBR data, indicating that the removed “noise” bands are valuable for hyperspectral classification, which should not be eliminated.
44
Nearest neighbor pattern classification
Thomas M. Cover, Peter E. Hart · IEEE Transactions on Information Theory · 1967 · 16.1K citations
De-noising by soft-thresholding
David L. Donoho · IEEE Transactions on Information Theory · 1995 · 9.6K citations
Ideal spatial adaptation by wavelet shrinkage
David L. Donoho, Iain M. Johnstone · Biometrika · 1994 · 7.8K citations
Clustering by Passing Messages Between Data Points
Brendan J. Frey, Delbert Dueck · Science · 2007 · 6.9K citations