Weighted sparse graph based dimensionality reduction for hyperspectral images
- Author
- Wei He, Hongyan Zhang, Liangpei Zhang, Wilfried Philips (UGent) and Wenzhi Liao (UGent)
- Organization
- Abstract
- Dimensionality reduction (DR) is an important and helpful preprocessing step for hyperspectral image (HSI) classification. Recently, sparse graph embedding (SGE) has been widely used in the DR of HSIs. In this letter, we propose a weighted sparse graph based DR (WSGDR) method for HSIs. Instead of only exploring the locality structure (as in neighborhood preserving embedding) or the linearity structure (as in SGE) of the HSI data, the proposed method couples the locality and linearity properties of HSI data together in a unified framework for the DR of HSIs. The proposed method was tested on two widely used HSI data sets, and the results suggest that the locality and linearity are complementary properties for HSIs. In addition, the experimental results also confirm the superiority of the proposed WSGDR method over the other state-of-the-art DR methods.
- Keywords
- sparse graph embedding, dimensionality reduction, nearest neighbor graph, hyperspectral image, weighted sparse coding, DISCRIMINANT-ANALYSIS, FEATURE-EXTRACTION
Downloads
-
WSR HSI DR edited revised.pdf
- full text
- |
- open access
- |
- |
- 659.40 KB
Citation
Please use this url to cite or link to this publication: http://hdl.handle.net/1854/LU-7135610
- MLA
- He, Wei, et al. “Weighted Sparse Graph Based Dimensionality Reduction for Hyperspectral Images.” IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, edited by Alejandro Frery, vol. 13, no. 5, IEEE, 2016, pp. 686–90, doi:10.1109/LGRS.2016.2536658.
- APA
- He, W., Zhang, H., Zhang, L., Philips, W., & Liao, W. (2016). Weighted sparse graph based dimensionality reduction for hyperspectral images. IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 13(5), 686–690. https://doi.org/10.1109/LGRS.2016.2536658
- Chicago author-date
- He, Wei, Hongyan Zhang, Liangpei Zhang, Wilfried Philips, and Wenzhi Liao. 2016. “Weighted Sparse Graph Based Dimensionality Reduction for Hyperspectral Images.” Edited by Alejandro Frery. IEEE GEOSCIENCE AND REMOTE SENSING LETTERS 13 (5): 686–90. https://doi.org/10.1109/LGRS.2016.2536658.
- Chicago author-date (all authors)
- He, Wei, Hongyan Zhang, Liangpei Zhang, Wilfried Philips, and Wenzhi Liao. 2016. “Weighted Sparse Graph Based Dimensionality Reduction for Hyperspectral Images.” Ed by. Alejandro Frery. IEEE GEOSCIENCE AND REMOTE SENSING LETTERS 13 (5): 686–690. doi:10.1109/LGRS.2016.2536658.
- Vancouver
- 1.He W, Zhang H, Zhang L, Philips W, Liao W. Weighted sparse graph based dimensionality reduction for hyperspectral images. Frery A, editor. IEEE GEOSCIENCE AND REMOTE SENSING LETTERS. 2016;13(5):686–90.
- IEEE
- [1]W. He, H. Zhang, L. Zhang, W. Philips, and W. Liao, “Weighted sparse graph based dimensionality reduction for hyperspectral images,” IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, vol. 13, no. 5, pp. 686–690, 2016.
@article{7135610,
abstract = {{Dimensionality reduction (DR) is an important and helpful preprocessing step for hyperspectral image (HSI) classification. Recently, sparse graph embedding (SGE) has been widely used in the DR of HSIs. In this letter, we propose a weighted sparse graph based DR (WSGDR) method for HSIs. Instead of only exploring the locality structure (as in neighborhood preserving embedding) or the linearity structure (as in SGE) of the HSI data, the proposed method couples the locality and linearity properties of HSI data together in a unified framework for the DR of HSIs. The proposed method was tested on two widely used HSI data sets, and the results suggest that the locality and linearity are complementary properties for HSIs. In addition, the experimental results also confirm the superiority of the proposed WSGDR method over the other state-of-the-art DR methods.}},
author = {{He, Wei and Zhang, Hongyan and Zhang, Liangpei and Philips, Wilfried and Liao, Wenzhi}},
editor = {{Frery, Alejandro}},
issn = {{1545-598X}},
journal = {{IEEE GEOSCIENCE AND REMOTE SENSING LETTERS}},
keywords = {{sparse graph embedding,dimensionality reduction,nearest neighbor graph,hyperspectral image,weighted sparse coding,DISCRIMINANT-ANALYSIS,FEATURE-EXTRACTION}},
language = {{eng}},
number = {{5}},
pages = {{686--690}},
publisher = {{IEEE}},
title = {{Weighted sparse graph based dimensionality reduction for hyperspectral images}},
url = {{http://doi.org/10.1109/LGRS.2016.2536658}},
volume = {{13}},
year = {{2016}},
}
- Altmetric
- View in Altmetric
- Web of Science
- Times cited: