PCA SVM classification for hyperspectral remote sensing images

摘要：

Hyperspectral image usually contains hundreds of bands, challenges conventional classification approaches. Due to the Hughs effect, only a few classifiers (such as support vector machine (SVM)) are able to handle high dimensional classification task. PCA transform is a conventional dimensionality reducing approach to determine the inherent dimensionality of image data. The experimental result from this paper indicates that bring in less informative PCA components will reduce the SVM classification accuracies.

关键词： SVM PCA hyperspectral remote senisng

作者: ZHANG Denghui MAO Shengyi

作者单位: College of Information and Technology Zhejiang Shuren University Hangzhou, China Guangzhou Institute of Geochemistry Chinese Academy of Sciences Guangzhou, China

会议类型: 国际会议

会议名称: 2010 International Conference on Circuit and Signal Processing(2010年电路与信号处理国际会议 ICCSP 2010)

会议地点: 上海

会议语种:英文

页码: 205-207

在线出版日期: 2010-12-25（万方平台首次上网日期，不代表论文的发表时间）