A Modified Locality-Preserving Projection Approach for Hyperspectral Image Classification

	A Modified Locality-Preserving Projection Approach for Hyperspectral Image Classification
	Zhai, Yongguang 1; Zhang, Lifu 1; Wang, Nan 1; Guo, Yi 1; Cen, Yi 1; Wu, Taixia 1; Tong, Qingxi 1
刊名	IEEE Geoscience and Remote Sensing Letters
	2016
卷号	13 期号:8 页码:1059-1063
关键词	NET PRIMARY PRODUCTION NORTHERN CHINA GLOBAL DROUGHT CLIMATE-CHANGE CARBON FLUXES TIME-SERIES TERM TRENDS ECOSYSTEM IMPACTS SUMMER
英文摘要	Locality-preserving projection (LPP) is a typical manifold-based dimensionality reduction (DR) method, which has been successfully applied to some pattern recognition tasks. However, LPP depends on an underlying adjacency graph, which has several problems when it is applied to hyperspectral image (HSI) processing. The adjacency graph is artificially created in advance, which may not be suitable for the following DR and classification. It is also difficult to determine an appropriate neighborhood size in graph construction. Additionally, only the information of local neighboring data points is considered in LPP, which is limited for improving classification accuracy. To address these problems, a modified version of the original LPP called MLPP is proposed for hyperspectral remote-sensing image classification. The idea is to select a different number of nearest neighbors for each data point adaptively and to focus on maximizing the distance between nonnearest neighboring points. This not only preserves the intrinsic geometric structure of the data but also increases the separability among ground objects with different spectral characteristics. Moreover, MLPP does not depend on any parameters or prior knowledge. Experiments on two real HSIs from different sensors demonstrate that MLPP is remarkably superior to other conventional DR methods in enhancing classification performance. © 2016 IEEE.
学科主题	Geochemistry & Geophysics; Engineering; Remote Sensing; Imaging Science & Photographic Technology
类目[WOS]	Geochemistry & Geophysics ; Engineering, Electrical & Electronic ; Remote Sensing ; Imaging Science & Photographic Technology
收录类别	SCI ; EI
语种	英语
WOS记录号	WOS:20162302465983
内容类型	期刊论文
源URL	[http://ir.radi.ac.cn/handle/183411/39272]
专题	遥感与数字地球研究所_SCI/EI期刊论文_期刊论文
作者单位	1. State Key Laboratory of Remote Sensing Sciences, Institute of Remote Sensing and Digital Earth (RADI), Chinese Academy of Sciences, Beijing 2.100101, China 3. College of Water Conservancy and Civil Engineering, Inner Mongolia Agricultural University, Hohhot 4.010018, China 5. School of Computing, Engineering and Mathematics, Parramatta South Campus Penrith South, Western Sydney University, Richmond 6.NSW 7.2751, Australia
推荐引用方式 GB/T 7714	Zhai, Yongguang,Zhang, Lifu,Wang, Nan,et al. A Modified Locality-Preserving Projection Approach for Hyperspectral Image Classification[J]. IEEE Geoscience and Remote Sensing Letters,2016,13(8):1059-1063.
APA	Zhai, Yongguang.,Zhang, Lifu.,Wang, Nan.,Guo, Yi.,Cen, Yi.,...&Tong, Qingxi.(2016).A Modified Locality-Preserving Projection Approach for Hyperspectral Image Classification.IEEE Geoscience and Remote Sensing Letters,13(8),1059-1063.
MLA	Zhai, Yongguang,et al."A Modified Locality-Preserving Projection Approach for Hyperspectral Image Classification".IEEE Geoscience and Remote Sensing Letters 13.8(2016):1059-1063.