Image Salt-Pepper Noise Elimination by Detecting Edges and Isolated Noise Points

  • Gang Li
  • Binheng Song
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3211)


It deals an algorithm for removing the impulse noise, which is also called salt-pepper noise, in this paper. By evaluating the absolute differences of intensity between each point and its neighbors, one can detect the edges, the isolated noise points and blocks. It needs to set up a set of simple rules to determine the corrupted pixels in a corrupted image. By successfully identifying the corrupted and uncorrupted pixels, especially for the pixels nearing the edges of a given image, one can eliminate random-valued impulse noise while preserving the detail of the image and its information of the edges. It shows, in the testing experiments, that it has a better performance for the algorithm than the other’s mentioned in the literatures.


Mean Square Error Median Filter Impulse Noise Central Pixel Noise Density 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Gabbouj, M., Coyle, E., Gallagher Jr., N.C.: An overview of median and stack filtering. Circuit System Signal Processing 11(1), 7–45 (1992)zbMATHCrossRefGoogle Scholar
  2. 2.
    Xutao, H.: Two-dimensional Digital Signal Processing II — Transformation and Median Filter. Science Press, Beijing (1985)Google Scholar
  3. 3.
    Chen, T., Wu, H.R.: Space Variant Median Filters for the Restoration of Impulse Noise Corrupted Images. IEEE Transactions on, Circuits and Systems II 8(48), 784–789 (2001)CrossRefGoogle Scholar
  4. 4.
    Turky, J.W.: Exploratory Data Analysis. Addison-Wesley, Reading (1971)Google Scholar
  5. 5.
    Pratt, W.K.: Median filtering, Semianual Report, Image Proc. Institute, Univ. of Southern California, pp.116–123 (1975) Google Scholar
  6. 6.
    Frieden, B.R.: A new restoring algorithm for the preferential enhancement of edge gradients. J. Opt. Soc. Amer. 66(3), 280–283 (1976)CrossRefMathSciNetGoogle Scholar
  7. 7.
    Ko, S.-J., Lee, Y.-H.: Center weighted median filters and their applications to image enhancement. IEEE Transactions on Circuits and Systems 9(38), 984–993 (1991)CrossRefGoogle Scholar
  8. 8.
    Nieminen, A., Heinonen, P., Neuvo, Y.: A new class of detail-preserving filters for image processing. IEEE Transactions on Pattern Analysis and Machine Intelligence 1(9), 74–90 (1987)CrossRefGoogle Scholar
  9. 9.
    Shutao, L., Yaonan, W.: Non-Linear Adaptive Removal of Salt and Pepper Noise from Images. Journal of Image and Graphics 12(5(a)) (2000)Google Scholar
  10. 10.
    Manglem Singh, K., Bora, P.K.: Improved Rank Conditioned Median Filter for Removal of Impulse Noise from Images. In: ProceedingsTENCON 2000, vol. 1, pp. 557–560 (2002)Google Scholar
  11. 11.
    Lin, H.M., Willson, A.N.: Median filters with adaptive length. IEEE CAS1 35(6), 675–690 (1988)MathSciNetGoogle Scholar
  12. 12.
    Florencio, D.A.F., Schafer, R.W.: Decision–based median filter using local signal statistics. In: Proc. SPIE, vol. 2308, pp. 268–275 (1994)Google Scholar
  13. 13.
    Hardie, R.E., Barner, K.E.: Rank conditioned rank selection filters for signal restoration. IEEE IP 3(2), 192–206 (1994)Google Scholar
  14. 14.
    Abreu, E., Lightone, M., Ketal, M.S.: A new efficient approach for the removal of impulse noise from highly corrupted images. IEEE IP 5(6), 1012–1025 (1996)Google Scholar
  15. 15.
    Eng, H.-L., Ma, K.-K.: Noise adaptive soft-switching median filter for image denoising. In: IEEE International Conference on 2000 6, 2175–2178 (2000)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • Gang Li
    • 1
  • Binheng Song
    • 1
  1. 1.School of SoftwareTsinghua UniversityBeijingP.R. China

Personalised recommendations