Advertisement

Modified LDE for Dimensionality Reduction of Hyperspectral Image

  • Lei He
  • Hongwei Yang
  • Lina ZhaoEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11903)

Abstract

Hyperspectral image (HSI) has shown promising results in many fields because of its high spectral resolution. However, redundancy and noise in spectral dimension seriously affect the classification of HSI. For this reason, many popular dimensionality reduction (DR) methods are proposed to solve the problem. The local discriminant embedding (LDE) as an effective non-linear method for DR can be more discriminative by constructing two neighborhood graphs. However, HSI is very easy influenced by noise, and the LDE algorithm based on K nearest neighborhood is highly susceptible to interference from extreme point, which may lead to inaccurate graph construction and poor performance of classification. To overcome the problem and retain the advantages of LDE, a modified local discriminant embedding (MLDE) is firstly applied on HSI by constructing neighborhood graphs on a new spectral feature space instead of the original space. We use variance to characterize the pixels similarity of the same class and use covariance to characterize the separation of different classes of pixels. The combination of variance and covariance makes pixels in the same class to be closer and makes greater separation of pixels from different classes, which enhances classification performance of HSI. The way of representing data by using variance and covariance can attenuate the effects of noise. The Log-Euclidean metric is used to capture the similarity between spectral vectors, which can provide a more accurate similarity evaluation than euclidean distance. The experimental results of two hyperspectral datasets demonstrate the effectiveness of our proposed MLDE method.

Keywords

Classification of hyperspectral image (HSI) Dimensionality reduction (DR) Local discriminant embedding (LDE) Log-Euclidean metric 

Notes

Acknowledgement

We would like to thank Prof. Wei Li for sharing the codes of LFDA, LGDA, SGDA, and SLGDA. We would also like to thank Changming Jia for offering the code of GDA-SS.

References

  1. 1.
    Lianru, G., Bin, Y., Qian, D., et al.: Adjusted spectral matched filter for target detection in hyperspectral imagery. Remote Sensing 7(6), 6611–6634 (2015)CrossRefGoogle Scholar
  2. 2.
    Zhang, L., Zhang, L., Tao, D., et al.: Hyperspectral remote sensing image subpixel target detection based on supervised metric learning. IEEE Trans. Geosci. Remote Sens. 52(8), 4955–4965 (2014)CrossRefGoogle Scholar
  3. 3.
    Onoyama, H., Ryu, C., Suguri, M., et al.: Integrate growing temperature to estimate the nitrogen content of rice plants at the heading stage using hyperspectral imagery. IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing 7(6), 2506–2515 (2014)CrossRefGoogle Scholar
  4. 4.
    Cheng, G., Zhu, F., Xiang, S., et al.: Semisupervised hyperspectral image classification via discriminant analysis and robust regression. IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing 9(2), 595–608 (2017)CrossRefGoogle Scholar
  5. 5.
    Jolliffe, I.T.: Principal component analysis. J. Mark. Res. 87(100), 513 (2002)zbMATHGoogle Scholar
  6. 6.
    Bandos, T.V., Bruzzone, L., Camps-Valls, G.: Classification of hyperspectral images with regularized linear discriminant analysis. IEEE Trans. Geosci. Remote Sens. 47(3), 862–873 (2009)CrossRefGoogle Scholar
  7. 7.
    Zhang, X., Liang, Y., Cahill, N.: Using superpixels to improve the efficiency of Laplacian Eigenmap based methods for target detection in hyperspectral imagery. In: Geoscience & Remote Sensing Symposium, IEEE (2016)Google Scholar
  8. 8.
    Wang, M., Yu, J., Niu, L., et al.: Unsupervised feature extraction for hyperspectral images using combined low rank representation and locally linear embedding. In: IEEE ICASSP 2017–2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) - New Orleans, LA, USA, 5 March 2017–9 March 2017, pp. 1428–1431 (2017)Google Scholar
  9. 9.
    Zhang, M., Jia, P., Shen, Y., et al.: Hyperspectral image classification method based on orthogonal NMF and LPP. In: Instrumentation & Measurement Technology Conference, IEEE (2016)Google Scholar
  10. 10.
    Sugiyama, M.: Dimensionality reduction of multimodal labeled data by local fisher discriminant analysis. J. Mach. Learn. Res. 8(1), 1027–1061 (2007)zbMATHGoogle Scholar
  11. 11.
    Li, W., Prasad, S., Fowler, J.E., et al.: Locality-preserving dimensionality reduction and classification for hyperspectral image analysis. IEEE Trans. Geosci. Remote Sens. 50(4), 1185–1198 (2012)CrossRefGoogle Scholar
  12. 12.
    Chen, H.T., Chang, H.W., Liu, T.L.: Local discriminant embedding and its variants. In: IEEE Computer Society Conference on Computer Vision & Pattern Recognition (2005Google Scholar
  13. 13.
    Yan, S., Xu, D., Zhang, B., et al.: Graph embedding: a general framework for dimensionality reduction. IEEE Trans. Pattern Anal. Mach. Intell. 29(1), 40 (2007)CrossRefGoogle Scholar
  14. 14.
    Cheng, B., Yang, J., Yan, S., et al.: Learning with 1-graph for image analysis. IEEE Trans. Image Process. 19(4), 858–866 (2010)MathSciNetCrossRefGoogle Scholar
  15. 15.
    Ly, N.H., Du, Q., Fowler, J.E.: Sparse graph-based discriminant analysis for hyperspectral imagery. IEEE Trans. Geosci. Remote Sens. 52(7), 3872–3884 (2014)CrossRefGoogle Scholar
  16. 16.
    Li, W., Liu, J., Du, Q.: Sparse and low-rank graph for discriminant analysis of hyperspectral imagery. IEEE Trans. Geosci. Remote Sens. 54(7), 1–12 (2016)CrossRefGoogle Scholar
  17. 17.
    Fubiao, F., Wei, L., Qian, D., et al.: Dimensionality reduction of hyperspectral image with graph-based discriminant analysis considering spectral similarity. Remote Sensing 9(4), 323 (2017)CrossRefGoogle Scholar
  18. 18.
    Deng, Y.J., Li, H.C., Pan, L., et al.: Modified tensor locality preserving projection for dimensionality reduction of hyperspectral images. IEEE Geosci. Remote Sens. Lett. 15(2), 277–281 (2018)CrossRefGoogle Scholar
  19. 19.
    Yang, X., Tu, S., Bai, Y., et al.: Fusion of intensity/coherent information using region covariance features for unsupervised classification of SAR imagery. In: Geoscience & Remote Sensing Symposium, IEEE (2016)Google Scholar
  20. 20.
    Yang, J., Xing, C., Chen, Y.: Improving the ScSPM model with Log-Euclidean Covariance matrix for scene classification. In: 2016 International Conference on Computer on Information and Telecommunication Systems (CITS), IEEE (2016)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.The Beijing University of Chemical TechnologyBeijingChina

Personalised recommendations