Customizing Kernel Functions for SVM-Based Hyperspectral Image Classification
Authors:
- Baofeng GuoBGBaofeng Guo
- James D. B. NelsonJNJames D. B. Nelson
- 14 March 2008
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 17 (4) , 622-629
Abstract
Previous research applying kernel methods such as support vector machines (SVMs) to hyperspectral image classification has achieved performance competitive with the best available algorithms. However, few efforts have been made to extend SVMs to cover the specific requirements of hyperspectral image classification, for example, by building tailor-made kernels. Observation of real-life spectral imagery from the AVIRIS hyperspectral sensor shows that the useful information for classification is not equally distributed across bands, which provides potential to enhance the SVM's performance through exploring different kernel functions. Spectrally weighted kernels are, therefore, proposed, and a set of particular weights is chosen by either optimizing an estimate of generalization error or evaluating each band's utility level. To assess the effectiveness of the proposed method, experiments are carried out on the publicly available 92AV3C dataset collected from the 220-dimensional AVIRIS hyperspectral sensor. Results indicate that the method is generally effective in improving performance: spectral weighting based on learning weights by gradient descent is found to be slightly better than an alternative method based on estimating ";relevance"; between band information and ground truth.Keywords
This publication has 21 references indexed in Scilit:
- Kernel-based methods for hyperspectral image classificationIEEE Transactions on Geoscience and Remote Sensing, 2005
- Classification of hyperspectral remote sensing images with support vector machinesIEEE Transactions on Geoscience and Remote Sensing, 2004
- Robust support vector method for hyperspectral data classification and knowledge discoveryIEEE Transactions on Geoscience and Remote Sensing, 2004
- Some recent results on hyperspectral image classification2004
- Classification of hyperspectral images with nonlinear filtering and support vector machines2003
- An assessment of support vector machines for land cover classificationInternational Journal of Remote Sensing, 2002
- Support vector machines for remote sensing image classification2001
- Linear spectral mixture models and support vector machines for remote sensingIEEE Transactions on Geoscience and Remote Sensing, 2000
- A Tutorial on Support Vector Machines for Pattern RecognitionData Mining and Knowledge Discovery, 1998
- Incorporating connected region labelling into automated image registration using mutual information1996