光学精密工程2018，Vol.26Issue(2)：450-460,11.DOI:10.3788/OPE.20182602.0450
面向高光谱图像分类的空谱判别分析
Spatial-spectral discriminant analysis for hyperspectral image classification
摘要
Abstract
The traditional hyperspectral image classification methods consider only spectral information while spatial information is ignored.To address this problem,a semi-supervised spatial-spectral glob-al and local discriminant analysis(S3GLDA)algorithm for hyperspectral image classification was pro-posed.T he method firstly made use of a few labeled samples to preserve the linear separability and global discriminant information of the data set,then the local discriminant information and nonlinear manifold was uncovered by the unlabeled spatial neighbors.The spectral-domain global discriminant structure and spatial-domain local discriminant structure were exploited simultaneously and the spatial information was incorporated into the output low-dimension features automatically,which constitute the semi-supervised spatial-spectral discriminant analysis.T he overall classification accuracies reached 76.24% and 82.96% on the Indian Pines and PaviaU data sets,respectively.Compared with several existing methods,the proposed algorithm can effectively improve the discriminant ability of the output features in the low-dimension subspace,w hich can uncover the intrinsic nonlinear multi-modal struc-ture of the data set and obtain higher ground objects classification accuracy.关键词
高光谱图像分类/特征提取/判别分析/空谱联合/半监督学习/空间近邻Key words
hyperspectral image classification/feature extraction/discriminant analysis/spatial-spec-tral/semi-supervised learning/spatial neighbors分类
信息技术与安全科学引用本文复制引用
侯榜焕,姚敏立,贾维敏,张峰干,王道平..面向高光谱图像分类的空谱判别分析[J].光学精密工程,2018,26(2):450-460,11.基金项目
国家自然科学基金资助项目(No.61401471) （No.61401471）
中国博士后基金资助项目(No.2014M562636) （No.2014M562636）
