Modified eigenvector-based feature extraction for hyperspectral image classification using limited samples


Classical supervised feature extraction methods, such as linear discriminant analysis (LDA) and nonparametric weighted feature extraction (NWFE), and search for projection directions through which the ratio of a between-class scatter matrix to a within-class scatter matrix can be maximized. The two feature extraction methods can obtain good classification results when training samples are sufficient; however, the effect is nonideal when samples are insufficient. In this study, the eigenvector spectra of LDA and NWFE are modified using spectral distribution information, which is locally unstable under the condition of a few samples. Experiments demonstrate that the proposed method outperforms several conventional feature extraction methods.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7


  1. 1.

    Hughes, G.F.: On the mean accuracy of statistical pattern recognition. IEEE Trans. Inf. Theory 14(1), 55–63 (1968)

    Article  Google Scholar 

  2. 2.

    Pan, B., Shi, Z., Xu, X.: MugNet: deep learning for hyperspectral image classification using limited samples. ISPRS J. Photogramm. Remote Sens. 145, 108–119 (2018)

    Article  Google Scholar 

  3. 3.

    Makantasis, K., et al.: Deep supervised learning for hyperspectral data classification through convolutional neural networks. In: International geoscience and remote sensing symposium (IGARSS 2015)

  4. 4.

    Pan, B., Shi, Z., Xu, X.: Analysis for the weakly pareto optimum in multiobjective-based hyperspectral band selection. IEEE Trans Geosci. Remote Sens. 57, 3729–3740 (2019)

    Article  Google Scholar 

  5. 5.

    Pan, B., et al.: CoinNet: copy initialization network for multispectral imagery semantic segmentation. IEEE Geosci. Remote Sens. Lett. 16, 816–820 (2019)

    Article  Google Scholar 

  6. 6.

    Shahdoosti, H.R., Mirzapour, F.: Spectral–spatial feature extraction using orthogonal linear discriminant analysis for classification of hyperspectral data. Eur. J. Remote Sens. 50(1), 111–124 (2017)

    Article  Google Scholar 

  7. 7.

    Kuo, B.C., Landgrebe, D.A.: Nonparametric weighted feature extraction for classification. IEEE Trans. Geosci. Remote Sens. 42(5), 1096–1105 (2004)

    Article  Google Scholar 

  8. 8.

    Kuo, B., Chang, K.: Feature extractions for small sample size classification problem[J]. IEEE Trans. Geosci. Remote. Sens. 45(3), 756–764 (2007)

    Article  Google Scholar 

  9. 9.

    Kuo, B.C., Li, C.H., Yang, J.M.: Kernel nonparametric weighted feature extraction for hyperspectral image classification. IEEE Trans. Geosci. Remote Sens. 47(4), 1139–1155 (2009)

    Article  Google Scholar 

  10. 10.

    Yang, J., Yu, P., Kuo, B.: A nonparametric feature extraction and Its application to nearest neighbor classification for hyperspectral image data. IEEE Trans. Geosci. Remote Sens. 48(3), 1279–1293 (2010)

    Article  Google Scholar 

  11. 11.

    Huang, H., Kuo, B.: Double nearest proportion feature extraction for hyperspectral-image classification. IEEE Trans. Geosci. Remote Sens. 48(11), 4034–4046 (2010)

    Google Scholar 

  12. 12.

    Jia, X., Kuo, B., Crawford, M.M.: Feature mining for hyperspectral image classification. Proc. IEEE 101(3), 676–697 (2013)

    Article  Google Scholar 

  13. 13.

    Imani, M., Ghassemian, H.: Band clustering-based feature extraction for classification of hyperspectral images using limited training samples. IEEE Geosci. Remote Sens. Lett. 11(8), 1325–1329 (2014)

    Article  Google Scholar 

  14. 14.

    Kamandar, M., Ghassemian, H.: Linear feature extraction for hyperspectral images based on information theoretic learning. IEEE Geosci. Remote Sens. Lett. 10(4), 702–706 (2013)

    Article  Google Scholar 

  15. 15.

    Wen, J., Tian, Z., Liu, X.: Neighborhood preserving orthogonal PNMF feature extraction for hyperspectral image classification. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 6(2), 759–768 (2013)

    Article  Google Scholar 

  16. 16.

    Sharma, A., Paliwal, K.K.: Linear discriminant analysis for the small sample size problem: an overview. Int. J. Mach. Learn. Cybern. 6(3), 443–454 (2014)

    Article  Google Scholar 

Download references


Funding was provided by the National Natural Science Foundation of China (Grant No. 61501456).

Author information



Corresponding author

Correspondence to Wenning Wang.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Wang, W., Mou, X. & Liu, X. Modified eigenvector-based feature extraction for hyperspectral image classification using limited samples. SIViP 14, 711–717 (2020).

Download citation


  • Eigenvector spectra
  • Feature extraction
  • Limited training sample classification
  • Hyperspectral image