Customizing kernel functions for SVM-based hyperspectral image classification
Customizing kernel functions for SVM-based hyperspectral image classification
复制标题
DOI：
10.1109/tip.2008.918955
复制
发表时间：
2008-04-01
影响因子：
10.6
通讯作者：
Nelson, James D. B.
中科院分区：
文献类型：
--
作者：
Guo, Baofeng;Gunn, Steve R.;Nelson, James D. B.
以前的研究应用核方法，如支持向量机（SVM）的高光谱图像分类取得了性能竞争力的最佳算法。然而，很少有人努力扩展支持向量机，以涵盖高光谱图像分类的特定要求，例如，通过构建量身定制的内核。从AVIRIS高光谱传感器的真实光谱图像的观察表明，有用的信息分类是不均匀分布在波段，这提供了潜在的，以提高支持向量机的性能，通过探索不同的核函数。因此，提出了谱加权核，并通过优化泛化误差估计或评估每个频带的效用水平来选择一组特定的权重。为了评估所提出的方法的有效性，进行了实验上公开的92AV3C数据集收集的220维AVIRIS高光谱传感器。结果表明，该方法通常是有效的，在提高性能：频谱加权的基础上通过梯度下降的学习权重被发现是略优于替代方法的基础上估计的“相关性”之间的频带信息和地面真理。
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.