Dimensionality reduction of hyperspectral data using discrete wavelet transform feature extraction
- 16 December 2002
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 40 (10), 2331-2338
- https://doi.org/10.1109/tgrs.2002.804721
Abstract
In this paper, the dyadic discrete wavelet transform is proposed for feature extraction from a high-dimensional data space. The wavelet's inherent multiresolutional properties are discussed in terms related to multispectral and hyperspectral remote sensing. Furthermore, various wavelet-based features are applied to the problem of automatic classification of specific ground vegetations from hyperspectral signatures. The wavelet transform features are evaluated using an automated statistical classifier. The system is tested using hyperspectral data for various agricultural applications. The experimental results demonstrate the promising discriminant capability of the wavelet-based features. The automated classification system consistently provides over 95% and 80% classification accuracy for endmember and mixed-signature applications, respectively. When compared to conventional feature extraction methods, the wavelet transform approach is shown to significantly increase the overall classification accuracy.Keywords
This publication has 11 references indexed in Scilit:
- Analysis of the effects of cover crop residue on hyperspectral reflectance discrimination of soybean and weeds via Haar transformPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Using wavelet transform of hyperspectral reflectance curves for automated monitoring of Imperata cylindrica (cogongrass)Published by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Wavelets for computationally efficient hyperspectral derivative analysisIEEE Transactions on Geoscience and Remote Sensing, 2001
- SAR image data compression using a tree-structured wavelet transformIEEE Transactions on Geoscience and Remote Sensing, 2001
- Detection of coastlines in SAR images using wavelet methodsIEEE Transactions on Geoscience and Remote Sensing, 2000
- Multiresolution-based image fusion with additive wavelet decompositionIEEE Transactions on Geoscience and Remote Sensing, 1999
- Remote Sensing Digital Image AnalysisPublished by Springer Science and Business Media LLC ,1999
- Multivariate Density EstimationWiley Series in Probability and Statistics, 1992
- A theory for multiresolution signal decomposition: the wavelet representationIeee Transactions On Pattern Analysis and Machine Intelligence, 1989
- The meaning and use of the area under a receiver operating characteristic (ROC) curve.Radiology, 1982