|
|
论文:2013,Vol:31,Issue(2):323-328 |
|
|
引用本文： |
|
|
温金环, 田铮, 赵永强, 延伟东. 基于局部保持线性判别嵌入特征提取的光谱图像分类[J]. 西北工业大学 |
|
|
Wen Jinhuan, Tian Zheng, Zhao Yongqiang, Yan Weidong. LPLDE (Locally Preserving Linear Discriminant Embedding) Method of Feature Extraction for Hyperspectral Image Classification[J]. Northwestern polytechnical university |
|
|
|
|
|
|
|
| 基于局部保持线性判别嵌入特征提取的光谱图像分类 |
|
| 温金环1, 田铮1, 赵永强2, 延伟东1 |
|
1. 西北工业大学 理学院应用数学系, 陕西 西安 710072;
2. 西北工业大学 自动化学院, 陕西 西安 710072 |
| 摘要: |
| 针对难于获得足够多的高光谱图像训练样本的问题,基于流形学习标准、Fisher标准和最大边缘标准,提出了一种适用于高光谱图像小样本问题的局部保持线性判别嵌入(LPLDE)监督线性流形学习特征提取方法。LPLDE方法利用类内近邻图和类间近邻图描述类内的紧性和类间的可分性,有效地避免了因类内离散度矩阵奇异导致的小样本问题,具有更好的判别性能,更适合于分类问题。高光谱数据的实验结果表明了该方法的有效性。 |
| 关键词:
特征提取
降维
流形学习
小样本问题
高光谱图像分类
|
|
| LPLDE (Locally Preserving Linear Discriminant Embedding) Method of Feature Extraction for Hyperspectral Image Classification |
|
| Wen Jinhuan1, Tian Zheng1, Zhao Yongqiang2, Yan Weidong1 |
|
1. Department of Applied Mathematics, Northwestern Polytechnical University, Xi'an 710072, China;
2. Department of Automatic Control, Northwestern Polytechnical University, Xi'an 710072, China |
| Abstract: |
| In view of the difficulty to get enough training samples in hyperspectral image,this paper presents a no-vel supervised linear manifold learning feature extraction method based on the manifold learning,Fisher criterionand Maximum Margin Criterion,named LPLDE by us,for hyperspectral image classification with nearest neighbor(NN) classifier. The intraclass compactness and interclass separability of hyperspectral data are respectively char-acterized by within-class neighboring graph and between-class neighboring graphs via embedding. The LPLDEmethod which efficiently avoids the within-class scatter matrix singularity caused by small-sample-size problem hasbetter discriminative performance and is more suitable for classification. Experimental results on hyperspectral data-sets and their analysis demonstrate preliminarily the efficiency of our LPLDE method as compared with other existingmethods. |
| Key words:
efficiency
experiments
feature extraction
image classification;dimensionality reduction
hyperspec-tral image classification
manifold learning
small-sample-size problem
|
|
| 收稿日期: 2012-05-26
修回日期:
|
| DOI: |
| 基金项目: 国家自然科学基金(61201323、11202161);西北工业大学基础研究基金(JC201053)资助 |
| 通讯作者:
Email： |
| 作者简介: 温金环(1974-),女,西北工业大学讲师,主要从事流形学习、非负矩阵分解及高光谱图像处理研究。
|
|
|
|
|
|
|
|
参考文献: |
|
|
[1] Kuo B C,Landgrebe D A. Nonparametric Weighted Feature Extraction for Classification. IEEE Trans on Geoscience and Re-mote Sensing, 2004, 42(5): 1096-1105
[2] Kuo B C,Li C H,Yang J M. Kernel Nonparametric Weighted Feature Extraction for Hyperspectral Image Classification. IEEETrans on Geoscience and Remote Sensing, 2009, 47(4):1139-1155
[3] Yang J M,Yu P T,Kuo B C. A Nonparametric Feature Extraction and Its Application to Nearest Neighbour Classification forHyperspectral Image Data. IEEE Trans on Geoscience and Remote Sensing, 2010, 48(3): 1279-1293
[4] Roweis S T,Saul L K. Nonlinear Dimensionality Reduction by Locally Linear Embedding. Science, 2000, 290(5000): 2323-2326
[5] Tenenbaum J B,de Silva V,Langford J C. A Global Geometric Framework for Nonlinear Dimensionality Reduction. Science,2000, 290(5500): 2319-2323
[6] Belkin M,Niyogi P. Laplacian Eigenmaps and Spectral Techniques for Embedding and Clustering. In Advances in Neural Infor-mation Processing System, 14,Cambridge,MA,USA, 2002, 585-591
[7] Bachmann C M,Ainsworth T L,Fusina R A. Exploiting Manifold Geometry in Hyperspectral Imagery. IEEE Trans on Geosci-ence and Remote Sensing, 2005, 43(3): 441-454
[8] Han T,Goodenough G. Nonlinear Feature Extraction of Hyperspectral Data Based on Locally Linear Embedding (LLE). IEEEInternational Geoscience and Remote Sensing Symposium, 2005, 1237-1240
[9] Qian S E,Chen G Y. A New Nonlinear Dimensionality Reduction Method with Application to Hyperspectral Image Analysis.IEEE International Geoscience and Remote Sensing Symposium, 2007, 270-273
[10] Mohan A,Sapiro G,Bosch E. Spatially Coherent Nonlinear Dimensionality Reduction and Segmentation of Hyperspectral Ima-ges. IEEE Geoscience and Remote Sensing Letters, 2007, 4(2):206-210
[11] He X F,Niyogi P. Locality Preserving Projections. Advances in Neural Information Processing System 16,MIT Press,Cam-bridge,MA, 2004, 153-160
[12] He X F,Cai D. Neighborhood Preserving Embedding. Proceedings of the 10th IEEE International Conference on Computer Vi-sion, 2005, 2:1208-1213
[13] Chen H,Chang H,Liu T. Local Discriminant Embedding and Its Variants. Proc 2005 International Conference on Computer Vi-sion and Pattern Recognition, 2005, 2: 846-853
[14] Yan S C, Xu D, Zhang B Y, et al. Graph Embedding: A General Framework for Dimensionality Reduction. Proceedings of Con-ference on Vision and Pattern Recognition, 2005, 29: 830-837
[15] Li H,Jiang T,Zhang K. Efficient and Robust Feature Extraction by Maximum Margin Criterion. IEEE Trans on Neural Net-works, 2006, 17:157-165 |
|
|
|
相关文献: |
|
|
1．温金环, 田铮, 林伟, 周敏, 延伟东.基于近邻保留PNMF特征提取的高光谱图像分类[J]. 西北工业大学, 2012,30(1): 138-144 |
|
|
|
|
|
|
