Customizing Kernel Functions for SVM-Based Hyperspectral Image Classification

• Published in: IEEE transactions on image processing 2008-04, Vol.17 (4), p.622-629
• Main Authors: Baofeng Guo, Gunn, S.R., Damper, R.I., Nelson, J.D.B.
• Format: Article
• Language: English
• Subjects: Algorithms; Applied sciences; Artificial Intelligence; Band spectra; Detection, estimation, filtering, equalization, prediction; Estimating; Exact sciences and technology; Gunn devices; Hyperspectral image processing; Hyperspectral imaging; Hyperspectral sensors; Image classification; Image Enhancement - methods; Image Interpretation, Computer-Assisted - methods; Image processing; Information, signal and communications theory; Kernel; Kernel functions; Kernels; Mutual information; mutual information (MI); Pattern Recognition, Automated - methods; Performance enhancement; Remote sensing; Reproducibility of Results; Sensitivity and Specificity; Sensors; Signal and communications theory; Signal processing; Signal Processing, Computer-Assisted; Signal representation. Spectral analysis; Signal, noise; Spectra; Studies; Support vector machine classification; Support vector machines; support vector machines (SVMs); Telecommunications and information theory
• ISSN: 1057-7149; 1941-0042
• DOI: 10.1109/TIP.2008.918955

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.