Customizing kernel functions for SVM-based hyperspectral image classification

Baofeng Guo

doi:10.1109/TIP.2008.918955

Customizing kernel functions for SVM-based hyperspectral image classification

2008-04-01

149

OA

AI

DOI：10.1109/TIP.2008.918955

Original

Original request for help

Save

Abstract

En 中文

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:

hyperspectral image processing

mutual information (MI)

remote sensing

support vector machines (SVMs)

Customizing kernel functions for SVM-based hyperspectral image classification

Abstract

Journal

Organization