Multimedia Tools and Applications

, Volume 76, Issue 4, pp 5873–5887 | Cite as

Contourlet domain SAR image de-speckling via self-snake diffusion and sparse representation

Article

Abstract

In this paper, A contourlet domain SAR image de-speckling algorithm via self-snake diffusion and sparse representation theory is presented in order to reduce the influence of the SAR image speckle noise on the large-scale target edge information of the low frequency subband and the texture information of the high frequency subband. For this algorithm, firstly, the contourlet transform is applied to the speckled SAR image, adjusts the directional number of each dimension to represent SAR image in the high dimensional space. Then, the low frequency subband without sparsity is filtered by self-snake diffusion and the filtered coefficient is regarded as the local average estimate of the low-frequency subband in the contourlet domain. Sparse representation optimization model of SAR image is presented for suppressing the speckle noise of the high frequency subbands with sparsity, and solves sparse coefficients of the high frequency subbands by using the improved orthogonal matching pursuit algorithm. Finally, the de-speckled image is reconstructed from all of the filtered subband coefficients by the inverse contourlet transform. This paper simulates three representative experiments and the experimental results demonstrate that the proposed algorithm has a better de-speckling performance with preserving the edge of the SAR image.

Keywords

Self-snake diffusion Sparse representation Contourlet transform Speckle noise Orthogonal matching pursuit algorithm 

References

  1. 1.
    Achim A, Tsakalides P, Bezerianos A (2003) SAR image denoising via Bayesian wavelet shrinkage based on heavy-tailed model. IEEE Trans Geosci Remote Sens 41(8):1773–1784CrossRefGoogle Scholar
  2. 2.
    Candes EJ, Romberg J, Tao T (2006) Robust uncertainty principles: exact signal reconstruction from highly incomplete frequency information. IEEE Trans Inf Theory 52(2):489–509MathSciNetCrossRefMATHGoogle Scholar
  3. 3.
    Candes EJ, Tao T (2006) Near-optimal signal recover from random projection: universal encoding strategies. IEEE Trans Inf Theory 52(12):5406–5425CrossRefMATHGoogle Scholar
  4. 4.
    Chen SB (2010) Research of de-speckling in SAR Image. Huazhong University of Science & TechnologyGoogle Scholar
  5. 5.
    Debotosh B (2014) Adaptive polar transform and fusion for human face image processing and evaluation. Hum Centric Comput Inf Sci 4(4):1–18Google Scholar
  6. 6.
    Foucher S (2008) SAR image filtering via learned dictionaries and sparse representations. IEEE Int Geosci Remote Sens Symp (IGARSS) 1(1):1229–1232Google Scholar
  7. 7.
    Ghimire D, Lee J (2014) Extreme learning machine ensemble using bagging for facial expression recognition. J Inf Process Syst 10(3):443–458CrossRefGoogle Scholar
  8. 8.
    Goodman JW (1976) Some fundamental properties of speckle. J Opt Soc Am B 66(11):1145–1150CrossRefGoogle Scholar
  9. 9.
    Hebar M, Gleich D, Cucej Z (2009) Autobinomial model for SAR image despeckling and information extraction. IEEE Trans Geosci Remote Sens 47(8):2818–2835CrossRefGoogle Scholar
  10. 10.
    Ji XX, Zhang G (2013) An improved orthogonal matching pursuit algorithm for blind sparsity signal reconstruction. J Astronaut 34(8):1146–1151Google Scholar
  11. 11.
    Khalighi SP, Fatemeh et al (2014) Iris recognition using robust localization and nonsubsampled contourlet based features. J Signal Process Syst 6(24):14–21Google Scholar
  12. 12.
    Li HJ, Zhang JS (2010) Image denoising based on the sparse land using redundant bandelet transform. J China Railw Soc 32(5):108–113Google Scholar
  13. 13.
    Liu SQ, Hu SH, Xiao Y (2012) Shearlet domain SAR image de-noising via sparse representation. J Electron Inf Technol 34(9):2110–2115CrossRefGoogle Scholar
  14. 14.
    Liu JL, Zuo BQ, Zeng XY (2014) The visual quality recognition of nonwovens using a novel wavelet based contourlet transform. Multimedia Tools Appl 70(3):1667–1684CrossRefGoogle Scholar
  15. 15.
    Ourabia, Soumya (2013) SAR images noise-removal method using the stationary contourlet transform. 2013 8th International Workshop on Systems. Signal Processing and Their Applications. WoSSPA. pp 429–434Google Scholar
  16. 16.
    Patel VM, Nasrabadi NM, Chellappa R (2010) Sparsity inspired automatic target recognition. Proceedings of SPIE 2010Google Scholar
  17. 17.
    Tosic I, Olshausen BA, Culpepper BJ (2011) Learning sparse representations of depth. IEEE J Sel Top Sign Proces 5(5):941–952CrossRefGoogle Scholar
  18. 18.
    Weickert J, Kühne G (2003) Fast methods for implicit active contour models U. Geometric level set methods in imaging, vision, and graphics. Part II: 43–57Google Scholar
  19. 19.
    Xu PF, Miao QG, Tang X et al (2014) A denoising algorithm via wiener filtering in the shearlet domain. Multimedia Tools Appl 71(3):1529–1558CrossRefGoogle Scholar
  20. 20.
    Yang M, Gong Z (2012) SAR image de-speckling using over-complete dictionary. Electron Lett 48(10):596–597CrossRefGoogle Scholar
  21. 21.
    Zhao RZ, Liu XY, Li CC (2009) Wavelet denoising via sparse representation. Sci China Ser F 52(8):1371–1377MathSciNetCrossRefMATHGoogle Scholar
  22. 22.
    Zhu L, Shui PL, Wu AJ. New algorithm for feducing speckle noise in the SAR image [J]. J Xidian Univ 39(2): 80–86Google Scholar

Copyright information

© Springer Science+Business Media New York 2015

Authors and Affiliations

  1. 1.Key Laboratory of Radar Imaging and Microwave Photonics, Ministry of EducationNanjing University of Aeronautics and AstronauticsNanjingChina
  2. 2.Jincheng CollegeNanjing University of Aeronautics and AstronauticsNanjingChina

Personalised recommendations