Advanced search
1 file | 6.11 MB Add to list

Research on supervised LPP feature extraction for hyperspectral image

Renbo Luo (UGent) , Youguo Pi and Wenzhi Liao (UGent)
Author
Organization
Abstract
For the classification among different land-cover types in a hyperspectral image, particularly in the small-sample-size problem, a feature extraction method is an approach for reducing the dimensionality and increasing the classification accuracy. A supervised principal locality preserving projection (SPLPP ) feature extraction algorithms, which uses the label information of training sample in locality preserving projection (LPP), was proposed in this paper. Three main steps are involved in the proposed SLPP: firstly uses PCA to remove redundant information, and then combines the label information in LPP, finally, SPLPP projects high-dimensional hyperspectral image into a low-dimensional space. Last but not least, SPLPP uses the extracted features as inputs of classifiers (e.g. support vector machine (SVM ) and K-nearest neighbors (KNN )) to do classification. Experimental results show that the proposed SPLPP has better local information retention ability and class discrimination ability compared with PCA, LPP, LDA
Keywords
Hyperspectral remote sensing image, Supervised principal locality preserving projection, Classification, Feature extraction

Downloads

  • (...).pdf
    • full text
    • |
    • UGent only
    • |
    • PDF
    • |
    • 6.11 MB

Citation

Please use this url to cite or link to this publication:

MLA
Luo, Renbo, Youguo Pi, and Wenzhi Liao. “Research on Supervised LPP Feature Extraction for Hyperspectral Image.” Ed. Ji Wu. REMOTE SENSING TECHNOLOGY AND APPLICATION 27.6 (2012): 46–52. Print.
APA
Luo, R., Pi, Y., & Liao, W. (2012). Research on supervised LPP feature extraction for hyperspectral image. (Ji Wu, Ed.)REMOTE SENSING TECHNOLOGY AND APPLICATION, 27(6), 46–52.
Chicago author-date
Luo, Renbo, Youguo Pi, and Wenzhi Liao. 2012. “Research on Supervised LPP Feature Extraction for Hyperspectral Image.” Ed. Ji Wu. Remote Sensing Technology and Application 27 (6): 46–52.
Chicago author-date (all authors)
Luo, Renbo, Youguo Pi, and Wenzhi Liao. 2012. “Research on Supervised LPP Feature Extraction for Hyperspectral Image.” Ed. Ji Wu. Remote Sensing Technology and Application 27 (6): 46–52.
Vancouver
1.
Luo R, Pi Y, Liao W. Research on supervised LPP feature extraction for hyperspectral image. Wu J, editor. REMOTE SENSING TECHNOLOGY AND APPLICATION. 2012;27(6):46–52.
IEEE
[1]
R. Luo, Y. Pi, and W. Liao, “Research on supervised LPP feature extraction for hyperspectral image,” REMOTE SENSING TECHNOLOGY AND APPLICATION, vol. 27, no. 6, pp. 46–52, 2012.
@article{5840655,
  abstract     = {{For the classification among different land-cover types in a hyperspectral image, particularly in the small-sample-size problem, a feature extraction method is an approach for reducing the dimensionality and increasing the classification accuracy. A supervised principal locality preserving projection (SPLPP ) feature extraction algorithms, which uses the label information of training sample in locality preserving projection (LPP), was proposed in this paper. Three main steps are involved in the proposed SLPP: firstly uses PCA to remove redundant information, and then combines the label information in LPP, finally, SPLPP projects high-dimensional hyperspectral image into a low-dimensional space. Last but not least, SPLPP uses the extracted features as inputs of classifiers (e.g. support vector machine (SVM ) and K-nearest neighbors (KNN )) to do classification. Experimental results show that the proposed SPLPP has better local information retention ability and class discrimination ability compared with PCA, LPP, LDA}},
  author       = {{Luo, Renbo and Pi, Youguo and Liao, Wenzhi}},
  editor       = {{Wu, Ji}},
  issn         = {{1004-0323}},
  journal      = {{REMOTE SENSING TECHNOLOGY AND APPLICATION}},
  keywords     = {{Hyperspectral remote sensing image,Supervised principal locality preserving projection,Classification,Feature extraction}},
  language     = {{chi}},
  number       = {{6}},
  pages        = {{46--52}},
  title        = {{Research on supervised LPP feature extraction for hyperspectral image}},
  volume       = {{27}},
  year         = {{2012}},
}