A feature extraction method for synthetic aperture radar (SAR) automatic target recognition based on maximum interclass distance

Article

Abstract

Synthetic aperture radar (SAR) automatic target recognition is an important application in SAR. How to extract features has restricted the application of SAR technology seriously. In this paper, a new feature extraction method for SAR automatic target recognition based on maximum interclass distance is proposed, which integrates class and neighborhood information. This method can reinforce discriminative power using maximum interclass distance, so it can improve recognition rate effectively.

Keywords

synthetic aperture radar (SAR) automatic target recognition (ATR) manifold learning feature extraction 

Referemces

  1. 1.
    Turk M, Pentland A P. Eigenface for recognition. J Neurosci, 1991, 3: 71–86Google Scholar
  2. 2.
    Belhumeur P N, Hespanaha P, Kriegman D J. Eigenface vs fisherfaces: Recognition using Class Specific Linear Projection. IEEE Trans Pattern Anal Mach Intell, 1997, 19: 711–720CrossRefGoogle Scholar
  3. 3.
    Mishra A K, Mulgrew B. Bistatic SAR ATR using PCA-based features. Proc SPIE, 2006, 6234: 62340U–9CrossRefGoogle Scholar
  4. 4.
    Mishra A K. Validation of PCA and LDA for SAR ATR. IEEE Region 10th Conference, 2008Google Scholar
  5. 5.
    Gunn S R. Support vector machines for classification and regression. Technical Report. Southampton: University of Southampton, 1998Google Scholar
  6. 6.
    Zhao Q, Principe J C. Support vector machines for SAR automatic target recognition. IEEE Trans Aerosp Electron Syst, 2001, 37(2): 643–654CrossRefGoogle Scholar
  7. 7.
    Li Y, Lei X G, Bai B D, et al. Information compression and speckle reduction for multifrequency polarimetric SAR images based on kernel PCA. J Syst Eng Electron, 2008, 19(3): 493–498CrossRefGoogle Scholar
  8. 8.
    Han P, Wu R B, Wang Y H, et al. An efficient SAR ATR approach. Proc IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP’03), Hongkong, 2003. 429–432Google Scholar
  9. 9.
    Lu H M, Fainman Y, Robert H N. Image manifolds. Proc SPIE, 1998, 3307: 52–63CrossRefGoogle Scholar
  10. 10.
    Tenenbaum J B, Silva V D, Langford J C. A global geometric framework for nonlinear dimensionality reduction. Science, 2000, 290: 2319–2323CrossRefGoogle Scholar
  11. 11.
    Belkin M, Niyogi P. Laplacian eigenmaps and spectral techniques for embedding and clustering. Adv Neural Inf Proc Syst, 2002, 14: 585–591Google Scholar
  12. 12.
    Roweis S T, Saul L K. Nonlinear dimensionality reduction by locally linear embedding. Science, 2000, 290: 2323–2326CrossRefGoogle Scholar
  13. 13.
    He X F, Niyogi P. Locality preserving projections. Adv Neural Inf Proc Syst, 2004, 16: 153–160Google Scholar
  14. 14.
    Kokiopoulou E, Saad Y. Orthogonal neighborhood preserving projections: A projeciton-based dimensionality reduction technique. IEEE Trans Pattern Anal Mach Intell, 2007, 29(12): 2143–2156CrossRefGoogle Scholar
  15. 15.
    Mishra A K, Mulgrew B. Bistatic SAR ATR. IET Radar Sonar and Navigation, 2007, 1: 459–469CrossRefGoogle Scholar
  16. 16.
    Costa J A, HeroIII A O. Manifold learning using euclidean k-nearest neighbour graphs. IEEE International Conference on Acoustics, Speech and Signal Processing—Proceedings, Montreal, 2004, 3: 988–991Google Scholar
  17. 17.
    Yan S C, Xu D, Zhang B Y, et al. Graph embedding and extensions: A general framework for dimensionality reduction. IEEE Trans Pattern Anal Mach Intell, 2007, 29: 40–51CrossRefGoogle Scholar
  18. 18.
    Fukunaga K. Introduction to Statistical Pattern Recognition. 2nd ed. Boston: Academic Press, 1990. 442–455MATHGoogle Scholar
  19. 19.
    Ross T, Worrell S, Velten V, et al. Standard SAR ATR evaluation experiment using the MSTAR public release dataset. Int Soc Opt Eng, 1998, 3370: 566–573Google Scholar
  20. 20.
    Wang T, Huang Y L, Wu J J, et al. SAR ATR based on generalized principal component analysis integrating class information. IET International Radar Conference, Guilin, 2009Google Scholar
  21. 21.
    Cover T M. Estimation by the nearest neighbor rule. IEEE Trans Inform Theo, 1968, 14: 50–55MATHCrossRefGoogle Scholar

Copyright information

© Science China Press and Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Bing Wang
    • 1
  • YuLin Huang
    • 1
  • JianYu Yang
    • 1
  • JunJie Wu
    • 1
  1. 1.School of Electronic EngineeringUniversity of Electronic Science and Technology of China (UESTC)ChenduChina

Personalised recommendations