Blind Noise Level Detection

  • Anna Tomaszewska
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7324)


In this paper we present a new fully automatic algorithm for blind noise level evaluation based on natural image statistics (NIS). Natural images are unprocessed reproductions of a natural scene observed by a human. During its evolution, the Human Visual System has been adjusted to the information encoded in natural images, making images interpreted best by a human when they fit NIS. The main requirement of such statistics is their striking regularity. Unfortunately, most computer images suffer from various artifacts, such as noise, that distort this regularity. Our contribution is applying the statistical behaviors for noise level evaluation. As most denoising algorithms require the user to specify the noise level automatization of the process makes it more usable and user independent. We compare the quality of our results to other algorithms.


noise level detection data restoration computer graphics 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Buccigrossi, R.W., Simoncelli, E.P.: Image Compression via Joint Statistical Characterization in Wavelet Domain. Proc. IEEE Transaction on Image Processing 8(12), 1688–1701 (1999)CrossRefGoogle Scholar
  2. 2.
    Simoncelli, E.P.: Statistical Modeling of Photographic Images. In: Handbook of Video and Image Processing, 2nd edn. Alan Bovik, Academic Press (2005)Google Scholar
  3. 3.
    Sheikh, H.R., Sabir, M.F., Bovik, A.C.: A Statistical Evaluation of Recent Full Reference Image Quality Assessment Algorithms. IEEE Transactions on Image Processing 15(11), 3441–3452 (2006)CrossRefGoogle Scholar
  4. 4.
    Liu, C., Freeman W.T., Szeliski R., Kang, S.B.: Noise Estimation from a Single Image. In: IEEE Conf. on Computer Vision and Pattern Recognition (2006)Google Scholar
  5. 5.
    Kaur, L., Gupta, S., Chauhan, R.C.: Image Denoising using Wavelet Thresholding. In: ICVGIP (2002)Google Scholar
  6. 6.
    Portilla, J., Strela, V., Wainwright, M., Simoncelli, E.P.: Image Denoising using Scale Mixtures of Gaussians in the Wavelet Domain. IEEE Transactions on Image Processing 12(11), 1338–1351 (2003)MathSciNetCrossRefGoogle Scholar
  7. 7.
    Tadmor, E., Nezzar, S., Vese, L.: A multiscale image representation using hierarchical (BV,L2) decompositions. Multiscale Model. Simul. (2), 554–579 (2004)Google Scholar
  8. 8.
    Yaroslavsky, L., Eden, M.: Fundamentals of Digital Optics. Birkhauser, Boston (1996)zbMATHGoogle Scholar
  9. 9.
    Liu, C., Szeliski, R., Kang, S.B., Zitnick, C.L., Freeman, W.T.: Automatic estimation and removal of noise from a single image. TPAMI 30(2), 299–314 (2008)CrossRefGoogle Scholar
  10. 10.
    Hasinoff, S.W., William, F.D., Freeman, T.: Noise-Optimal Capture for High Dynamic Range PhotographyGoogle Scholar
  11. 11.
    Coifman, R.R., Donoho, D.: Translation-invariant de-noising. Wavelets and Statistics, pp. 125–150. Springer (1995)Google Scholar
  12. 12.
    Donoho, D., Johnstone, I.: Ideal spatial adaptation via wavelet shrinkage. Biometrika 81, 425–455 (1994)MathSciNetzbMATHCrossRefGoogle Scholar
  13. 13.
    Buades, A., Coll, B., Morel, J.M.: A review of image denoising algorithms, with the new one, multiscale model simulation. Society for Industrial and Applied Mathematics 4(2), 490–530 (2005)MathSciNetzbMATHGoogle Scholar
  14. 14.
    Buccigrossi, R.W., Simoncelli, E.P.: Image Compression via Joint Statistical Characterization in the Wavelet Domain. IEEE Transactions on Image Processing 8, 1688–1701 (1999)CrossRefGoogle Scholar
  15. 15.
    Simoncelli, E.: Statistical Models for Images: Compression, Restoration and Synthesis. In: 31st Asilomar Conf. on Signals, Systems and Computers, pp. 673–678. IEEE Computer Society (1997)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Anna Tomaszewska
    • 1
  1. 1.Faculty of Computer ScienceWest Pomeranian University of Technology in SzczecinSzczecinPoland

Personalised recommendations