文章基本信息

标题：Hyperspectral Images Terrain Classification in Combination Spectrum DLDA Subspace
本地全文：下载
作者：Liu, Jing ; Liu, Yi ; Wu, Jin 等
期刊名称：Journal of Computers
印刷版ISSN：1796-203X
出版年度：2014
卷号：9
期号：1
页码：28-33
DOI：10.4304/jcp.9.1.28-33
语种：English
出版社：Academy Publisher
摘要：Hyperspectral images face the problem of high dimensionality and lowsamples number, which results in unsatisfied recognition efficiency, thus dimensionalityreduction is needed before terrain classification. A novel hyperspectral imagesfeature extraction method is presented for dimensionality reduction. Firstly,take discrete Fourier transformation (DFT) of each pixel spectral curve, andcombine the amplitude spectrum and corresponding phase spectrum; then directlinear discriminant analysis (DLDA) is performed in the combination spectrumspace to extract features. Minimum distance classifier is used to evaluate thefeature extraction performance in the achievedcombination spectrum DLDA subspace. The experimental results for airbornevisible/infrared imaging spectrometer (AVIRIS) hyperspectral image show that,comparing with the spectral DLDA subspace method, the present method canimprove the terrain classification efficiency.
关键词：Terrain classification;Feature subspace;Feature extraction;Hyperspectral image