Advertisement

Fast Parameter Sensitivity Analysis of PDE-Based Image Processing Methods

  • Torben Pätz
  • Tobias Preusser
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7578)

Abstract

We present a fast parameter sensitivity analysis by combining recent developments from uncertainty quantification with image processing operators. The approach is not based on a sampling strategy, instead we combine the polynomial chaos expansion and stochastic finite elements with PDE-based image processing operators. With our approach and a moderate number of parameters in the models the full sensitivity analysis is obtained at the cost of a few Monte Carlo runs. To demonstrate the efficiency and simplicity of the approach we show a parameter sensitivity analysis for Perona-Malik diffusion, random walker and Ambrosio-Tortorelli segmentation, and discontinuity-preserving optical flow computation.

Keywords

Polynomial Chaos Stochastic Parameter Polynomial Chaos Expansion Parameter Sensitivity Analysis Stochastic Heat Equation 
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.

References

  1. 1.
    Pirsiavash, H., Kasaei, S., Marvasti, F.: An efficient parameter selection criterion for image denoising. In: Proceedings of the Fifth IEEE ISSPIT, pp. 872–877 (2005)Google Scholar
  2. 2.
    Zhu, X., Milanfar, P.: Automatic parameter selection for denoising algorithms using a no-reference measure of image content. IEEE T. Image Proc. 19, 3116–3132 (2010)MathSciNetCrossRefGoogle Scholar
  3. 3.
    Lin, Y., Wohlberg, B., Guo, H.: UPRE method for total variation parameter selection. Signal Processing 90, 2546–2551 (2010)zbMATHCrossRefGoogle Scholar
  4. 4.
    Zimmer, H., Bruhn, A., Weickert, J.: Optic flow in harmony. International Journal of Computer Vision 93, 368–388 (2011)MathSciNetzbMATHCrossRefGoogle Scholar
  5. 5.
    Saltelli, A., Tarantola, S., Campolongo, F., Ratto, M.: Sensitivity analysis in practice: a guide to assessing scientific models. Wiley (2004)Google Scholar
  6. 6.
    Cacuci, D., Ionescu-Bujor, M., Navon, I.: Sensitivity and Uncertainty Analysis: Applications to large-scale systems. Chapman & Hall/CRC Press (2005)Google Scholar
  7. 7.
    Steger, T.R., White, R.A., Jackson, E.F.: Input parameter sensitivity analysis and comparison of quantification models for continuous arterial spin labeling. Magnetic Resonance in Medicine 53, 895–903 (2005)CrossRefGoogle Scholar
  8. 8.
    Blackmore, B.: Validation and sensitivity analysis of an image processing technique to derive thermal conductivity variation within a printed circuit board. In: 25th Semiconductor Thermal Measurement and Management Symposium, pp. 76–86 (2009)Google Scholar
  9. 9.
    Zhang, Y., Goldgof, D.B., Sarkar, S., Tsap, L.V.: A sensitivity analysis method and its application in physics-based nonrigid motion modeling. Image and Vision Computing 25, 262–273 (2007)CrossRefGoogle Scholar
  10. 10.
    Oakley, J.E., O’Hagan, A.: Probabilistic sensitivity analysis of complex models: A bayesian approach. J. Roy. Statist. Soc. Ser. B 66, 751–769 (2002)MathSciNetCrossRefGoogle Scholar
  11. 11.
    Preusser, T., Scharr, H., Krajsek, K., Kirby, R.: Building blocks for computer vision with stochastic partial differential equations. Int. J. Comput. Vis. 80, 375–405 (2008)CrossRefGoogle Scholar
  12. 12.
    Pätz, T., Preusser, T.: Ambrosio-Tortorelli Segmentation of Stochastic Images. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part V. LNCS, vol. 6315, pp. 254–267. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  13. 13.
    Xiu, D., Karniadakis, G.E.: The Wiener–Askey polynomial chaos for stochastic differential equations. SIAM Journal on Scientific Computing 24, 619–644 (2002)MathSciNetzbMATHCrossRefGoogle Scholar
  14. 14.
    Ghanem, R.G., Spanos, P.D.: Stochastic finite elements: a spectral approach. Springer, New York (1991)zbMATHCrossRefGoogle Scholar
  15. 15.
    Perona, P., Malik, J.: Scale-space and edge detection using anisotropic diffusion. IEEE Trans. Pattern Anal. Mach. Intell. 12, 629–639 (1990)CrossRefGoogle Scholar
  16. 16.
    Grady, L.: Random walks for image segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence 28, 1768–1783 (2006)CrossRefGoogle Scholar
  17. 17.
    Horn, B.K.P., Schunck, B.G.: Determining optical flow. Artificial Intelligence 17, 185–203 (1981)CrossRefGoogle Scholar
  18. 18.
    Metropolis, N., Ulam, S.: The Monte Carlo method. Journal of the American Statistical Association 44, 335–341 (1949)MathSciNetzbMATHCrossRefGoogle Scholar
  19. 19.
    Wiener, N.: The homogeneous chaos. Am. J. Math. 60, 897–936 (1938)MathSciNetCrossRefGoogle Scholar
  20. 20.
    Catté, F., Lions, P.L., Morel, J.M., Coll, T.: Image selective smoothing and edge detection by nonlinear diffusion. SIAM J. Numer. Anal. 29, 182–193 (1992)MathSciNetzbMATHCrossRefGoogle Scholar
  21. 21.
    Debusschere, B.J., Najm, H.N., Pébay, P.P., Knio, O.M., Ghanem, R.G., Le Maître, O.P.: Numerical challenges in the use of polynomial chaos representations for stochastic processes. SIAM Journal on Scientific Computing 26, 698–719 (2005)CrossRefGoogle Scholar
  22. 22.
    Pätz, T., Preusser, T.: Segmentation of stochastic images with a stochastic random walker method. IEEE Transactions on Image Processing 21, 2424–2433 (2012)CrossRefGoogle Scholar
  23. 23.
    McCane, B., Novins, K., Crannitch, D., Galvin, B.: On benchmarking optical flow. Computer Vision and Image Understanding 84, 126–143 (2001)zbMATHCrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Torben Pätz
    • 1
    • 2
  • Tobias Preusser
    • 1
    • 2
  1. 1.School of Engineering and ScienceJacobs University BremenGermany
  2. 2.Fraunhofer MEVISBremenGermany

Personalised recommendations