Stochastic Resonance and Mean Shift Filtering for Detecting Weak Features in Noisy Images

Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 222)


Stochastic Resonance has been shown to occur in many biological, physical and geological systems, resulting in the boosting of weak signals to make them detectable. In the image processing domain, narrow regions, small features and low-contrast or subtle edges, especially in noisy images, correspond to such weak signals. We show, both mathematically and empirically, that stochastic resonance occurs and may be exploited in the detection, extraction and analysis of such features. These mathematical results are confirmed by simulation studies. Finally, results on standard images such as cameraman, boats, lena, etc. demonstrate that several subtle features lost by the application of robust techniques such as Mean Shift filter are recovered by stochastic resonance. These results reconfirm the mathematical and simulation findings.


Stochastic resonance Robust techniques Mean-shift filter 


  1. 1.
    Taylor JS, Cristianini N (2004) Kernel methods for pattern analysis. Cambridge University Press, New YorkGoogle Scholar
  2. 2.
    Hampel FR, Rousseeuw PJ, Ronchetti E, Stahel WA (1986) Robust statistics: the approach based on influence functions. Wiley, New YorkGoogle Scholar
  3. 3.
    Huber PJ (1981) Robust statistics. Wiley, New YorkGoogle Scholar
  4. 4.
    Fischler MA, Bolles RC (1981) Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Comm ACM 24(6):381–395Google Scholar
  5. 5.
    Stewart CV (1995) MINPRAN: a new robust estimator for computer vision. IEEE Trans Pattern Anal Mach Intell 17:925–938Google Scholar
  6. 6.
    Comaniciu D, Meer P (1999) Mean shift analysis and applications. In: Proceedings of the 7th IEEE international conference on computer vision (ICCV99), vol 2, pp 1197–1203Google Scholar
  7. 7.
    Comaniciu D, Meer P (2002) Mean shift: a robust approach toward feature space analysis. IEEE Trans Pattern Anal Mach Intell 24(5):603–619Google Scholar
  8. 8.
    Gammaitoni L et al (1998) Stochastic resonance. Rev Mod Phys 70(1):223Google Scholar
  9. 9.
    Jha RK, Biswas PK, Chatterji BN (2005) Image denoising using stochastic resonance. In: Proceedings of the international conference on cognition and recognition, MysoreGoogle Scholar
  10. 10.
    Benzi R, Sutera A, Vulpiani A (1981) The mechanism of stochastic resonance. J Physics A 14:L453Google Scholar
  11. 11.
    Benzi R, Parisi G, Sutera A, Vulpiani A (1982) Stochastic resonance in climatic change. Tellus 34(1):10–16Google Scholar
  12. 12.
    Benzi R, Sutera A, Parisi G, Vulpiani A (1983) A theory of stochastic resonance in climate change. SIAM (Soc Ind Appl Math) J Appl Math 43:565Google Scholar
  13. 13.
    Fauve S, Heslot F (1983) Stochastic resonance in a bistable system. Phys Lett 97A:5Google Scholar
  14. 14.
    McNamara B, Wiesenfeld K, Roy R (1988) Phys Rev Lett 60:2626CrossRefGoogle Scholar
  15. 15.
    Winbing Tao YZ, Jin H (2007) Color image segmentation based on mean shift and normalized cuts. IEEE Trans Syst Man Cybern 37:1382--1389Google Scholar
  16. 16.
    Wiesenfeld K, Wellens T, Buchleitner A (2002) Coherent evolution in noisy environments. Springer, BerlinGoogle Scholar
  17. 17.
    Wellens T, Shatokhin V, Buchleitner A (2004) Stochastic resonance. Rep Prog Phys 67(1):45–105CrossRefGoogle Scholar
  18. 18.
    Pascual JC, Ordonez JG, Morillo M (2005) Stochastic resonance: theory and numerics. Chaos 15:1–12Google Scholar
  19. 19.
    Greenwood PE, Muller UU, Ward LM, Wefelmeyer W (2003) Statistical analysis of stochastic resonance in a thresholded detector. Austrian J Stat 32(1,2):49–70Google Scholar
  20. 20.
    Müller UU (2000) Nonparametric regression for threshold data. Canadian J Stat 28:301310Google Scholar
  21. 21.
    Canny JF (1986) A theory of edge detection. IEEE Trans Pattern Anal Mach Intell 8:147–163Google Scholar

Copyright information

© Springer India 2013

Authors and Affiliations

  1. 1.Dept. of Computer and Information SciencesUniversity of HyderabadHyderabadIndia

Personalised recommendations