Journal of Mathematical Imaging and Vision

, Volume 36, Issue 3, pp 201–226 | Cite as

Multiplicative Noise Removal Using L1 Fidelity on Frame Coefficients

Article

Abstract

We address the denoising of images contaminated with multiplicative noise, e.g. speckle noise. Classical ways to solve such problems are filtering, statistical (Bayesian) methods, variational methods, and methods that convert the multiplicative noise into additive noise (using a logarithmic function), apply a variational method on the log data or shrink their coefficients in a frame (e.g. a wavelet basis), and transform back the result using an exponential function.

We propose a method composed of several stages: we use the log-image data and apply a reasonable under-optimal hard-thresholding on its curvelet transform; then we apply a variational method where we minimize a specialized hybrid criterion composed of an 1 data-fidelity to the thresholded coefficients and a Total Variation regularization (TV) term in the log-image domain; the restored image is an exponential of the obtained minimizer, weighted in a such way that the mean of the original image is preserved. Our restored images combine the advantages of shrinkage and variational methods and avoid their main drawbacks. Theoretical results on our hybrid criterion are presented. For the minimization stage, we propose a properly adapted fast scheme based on Douglas-Rachford splitting. The existence of a minimizer of our specialized criterion being proven, we demonstrate the convergence of the minimization scheme. The obtained numerical results clearly outperform the main alternative methods especially for images containing tricky geometrical structures.

Curvelets Douglas-Rachford splitting 1 data-fidelity Multiplicative noise removal Nonsmooth optimization Proximal calculus Tight frames TV regularization Variational methods 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Abramowitz, M., Stegun, I.A.: Handbook of Mathematical Functions. Dover, New York (1972) MATHGoogle Scholar
  2. 2.
    Acar, R., Vogel, C.: Analysis of bounded variation penalty methods for ill-posed problems. IEEE Trans. Image Process. 10(6), 1217–1229 (1994) MATHMathSciNetGoogle Scholar
  3. 3.
    Achim, A., Bezerianos, A., Tsakalides, P.: Novel bayesian multiscale method for speckle removal in medical ultrasound images. IEEE Trans. Med. Imag. 20(8), 772–783 (2001) CrossRefGoogle Scholar
  4. 4.
    Achim, A., Kuruoglu, E., Zerubia, J.: SAR image filtering based on the heavy-tailed Rayleigh model. IEEE Trans. Image Process. 15(9), 2686–2693 (2006) CrossRefGoogle Scholar
  5. 5.
    Achim, A., Tsakalides, P., Bezerianos, A.: SAR image denoising via bayesian wavelet shrinkage based on heavy-tailed modeling. IEEE Trans. Geosci. Remote Sens. 41(8), 1773–1784 (2003) CrossRefGoogle Scholar
  6. 6.
    Antoniadis, A., Fan, J.: Regularization of wavelet approximations. J. Acoust. Soc. Am. 96(455), 939–967 (2001) MATHMathSciNetGoogle Scholar
  7. 7.
    Antoniadis, A., Leporini, D., Pesquet, J.-C.: Wavelet thresholding for some classes of non-Gaussian noise. Stat. Neerl. 56(4), 434–453 (2002) MATHCrossRefMathSciNetGoogle Scholar
  8. 8.
    Aubert, G., Aujol, J.-F.: A variational approach to remove multiplicative noise. SIAM J. Appl. Math. 68(4), 925–946 (2008) MATHCrossRefMathSciNetGoogle Scholar
  9. 9.
    Aubert, G., Kornprobst, P.: Mathematical Problems in Image Processing, 2nd edn. Springer, Berlin (2006) MATHGoogle Scholar
  10. 10.
    Aujol, J.-F.: Some first-order algorithms for total variation based image restoration. J. Math. Imag. Vis. 34(3), 307–327 (2009) CrossRefMathSciNetGoogle Scholar
  11. 11.
    Belge, M., Kilmer, M., Miller, E.: Wavelet domain image restoration with adaptive edge-preserving regularization. IEEE Trans. Image Process. 9(4), 597–608 (2000) MATHCrossRefGoogle Scholar
  12. 12.
    Beck, A., Teboulle, M.: A fast iterative shrinkage-thresholding algorithm for linear inverse problems. SIAM J. Imag. Sci. 2(1), 183–202 (2009) MATHCrossRefMathSciNetGoogle Scholar
  13. 13.
    Bobichon, Y., Bijaoui, A.: Regularized multiresolution methods for astronomical image enhancement. Exp. Astron. 7, 239–255 (1997) CrossRefGoogle Scholar
  14. 14.
    Candès, E.J., Donoho, D., Ying, L.: Fast discrete curvelet transforms. SIAM Multiscale Model. Simul. 5(3), 861–899 (2005) CrossRefGoogle Scholar
  15. 15.
    Candès, E.J., Guo, F.: New multiscale transforms, minimum total variation synthesis. Applications to edge-preserving image reconstruction. Signal Process. 82 (2002) Google Scholar
  16. 16.
    Chambolle, A., Darbon, J.: On total variation minimization and surface evolution using parametric maximum flows. Technical report, CMAP-04, Ecole Polytechnique, France (2004) Google Scholar
  17. 17.
  18. 18.
    Chambolle, A.: An algorithm for total variation minimization and application. J. Math. Imag. Vis. 20(1) (2004) Google Scholar
  19. 19.
    Chambolle, A.: Total variation minimization and a class of binary MRF models. Lect. Notes Comput. Sci. 3757, 136–152 (2005) CrossRefGoogle Scholar
  20. 20.
    Chan, T.F., Zhou, H.M.: Total variation improved wavelet thresholding in image compression. In: Proc. of the IEEE Int. Conf. on Image Processing, vol. 2, pp. 391–394. IEEE Press, New York (2000) Google Scholar
  21. 21.
    Charbonnier, P., Blanc-Féraud, L., Aubert, G., Barlaud, M.: Deterministic edge-preserving regularization in computed imaging. IEEE Trans. Image Process. 6(2), 298–311 (1997) CrossRefGoogle Scholar
  22. 22.
    Chesneau, C., Fadili, M.J., Starck, J.-L.: Stein block thresholding for image denoising. Appl. Comput. Harmon. Anal. Revised Google Scholar
  23. 23.
    Coifman, R.R., Donoho, D.: Translation-invariant de-noising. In: Antoniadis, A., Oppenheim, G. (eds.) Wavelets and Statistics. Department of Statistics (1995) Google Scholar
  24. 24.
    Coifman, R.R., Sowa, A.: Combining the calculus of variations and wavelets for image enhancement. Appl. Comput. Harmon. Anal. 9(1), 1–18 (2000) MATHCrossRefMathSciNetGoogle Scholar
  25. 25.
    Combettes, P.L.: Solving monotone inclusions via compositions of nonexpansive averaged operators. Optimization 53(5) (2004) Google Scholar
  26. 26.
    Combettes, P.L., Pesquet, J.-C.: A Douglas-Rachford splitting approach to nonsmooth convex variational signal recovery. IEEE J. Sel. Top. Signal Process. 1(4), 564–574 (2007) CrossRefGoogle Scholar
  27. 27.
    Combettes, P.L., Wajs, V.R.: Signal recovery by proximal forward-backward splitting. SIAM Multiscale Model. Simul. 4(4), 1168–1200 (2005) MATHCrossRefMathSciNetGoogle Scholar
  28. 28.
    Darbon, J., Sigelle, M., Tupin, F.: The use of levelable regularization functions for MRF restoration of SAR images while preserving reflectivity. In: Proc. of IS&T/SPIE 19th Annual Symposium Electronic Imaging, p. 6490, San Jose (USA) (Feb. 2007) Google Scholar
  29. 29.
    Denis, L., Tupin, F., Darbon, J., Sigelle, M.: SAR Image Regularization with Fast Approximate Discrete Minimization. IEEE Trans. Image Process. 18(7), 1588–1600 (2009) CrossRefGoogle Scholar
  30. 30.
    Donoho, D.L., Johnstone, I.M.: Ideal spatial adaptation by wavelet shrinkage. Biometrika 81(3), 425–455 (1994) MATHCrossRefMathSciNetGoogle Scholar
  31. 31.
    Donoho, D.L., Johnstone, I.M.: Adapting to unknown smoothness via wavelet shrinkage. J. Acoust. Soc. Am. 90 (1995) Google Scholar
  32. 32.
    Durand, S., Nikolova, M.: Denoising of frame coefficients using l 1 data-fidelity term and edge-preserving regularization. SIAM J. Multiscale Model. Simul. 6(2), 547–576 (2007) MATHCrossRefMathSciNetGoogle Scholar
  33. 33.
    Durand, S., Froment, J.: Reconstruction of wavelet coefficients using total variation minimization. SIAM J. Sci. Comput. 24(5), 1754–1767 (2003) MATHCrossRefMathSciNetGoogle Scholar
  34. 34.
    Eckstein, J., Bertsekas, D.P.: On the Douglas-Rachford splitting method and the proximal point algorithm for maximal monotone operators. Math. Program., Ser. A and B 55(3), 293–318 (1992) MATHCrossRefMathSciNetGoogle Scholar
  35. 35.
    Eckstein, J., Svaiter, B.F.: A family of projective splitting methods for the sum of two maximal monotone operators. Math. Program., Ser. B 111(1) (2008) Google Scholar
  36. 36.
    Froment, J., Durand, S.: Artifact free signal denoising with wavelets. In: Proceedings of the IEEE Int. Conf. on Acoustics, Speech and Signal Processing, vol. 6 (2001) Google Scholar
  37. 37.
    Fukuda, S., Hirosawa, H.: Suppression of speckle in synthetic aperture radar images using wavelet. Int. J. Remote Sens. 19(3), 507–519 (1998) CrossRefGoogle Scholar
  38. 38.
    Gabay, D.: In: Fortin, M., Glowinski, R. (eds.) Applications of the Method of Multipliers to Variational Inequalities. North-Holland, Amsterdam (1983) Google Scholar
  39. 39.
    Huang, Y.-M., Ng, M.K., Wen, Y.-W.: A new total variation method for multiplicative noise removal. SIAM J. Imag. Sci. 2(1), 20–40 (2009) MATHCrossRefMathSciNetGoogle Scholar
  40. 40.
    Krissian, K., Westin, C.-F., Kikinis, R., Vosburgh, K.G.: Oriented speckle reducing anisotropic diffusion. IEEE Trans. Image Process. 16(5), 1412–1424 (2007) CrossRefMathSciNetGoogle Scholar
  41. 41.
    Lions, P.-L.: Une méthode itérative de resolution d’une inéquation variationnelle. Isr. J. Math. 31(2), 204–208 (1978) MATHCrossRefGoogle Scholar
  42. 42.
    Lions, P.-L., Mercier, B.: Splitting algorithms for the sum of two nonlinear operators. SIAM J. Numer. Anal. 16(6), 964–979 (1979) MATHCrossRefMathSciNetGoogle Scholar
  43. 43.
    Malgouyres, F.: Mathematical analysis of a model which combines total variation and wavelet for image restoration. J. Inf. Process. 2(1), 1–10 (2002) Google Scholar
  44. 44.
    Malgouyres, F.: Minimizing the total variation under a general convex constraint for image restoration. IEEE Trans. Image Process. 11(12), 1450–1456 (2002) CrossRefMathSciNetGoogle Scholar
  45. 45.
    Moreau, J.-J.: Fonctions convexes duales et points proximaux dans un espace hilbertien. C. R. Acad. Sci., Sér. A Math. 255, 2897–2899 (1962) MATHMathSciNetGoogle Scholar
  46. 46.
    Moulin, P., Liu, J.: Analysis of multiresolution image denoising schemes using generalized Gaussian and complexity priors. IEEE Trans. Image Process. 45(3), 909–919 (1999) MATHMathSciNetGoogle Scholar
  47. 47.
    Nesterov, Y.: Gradient methods for minimizing composite objective function. Technical report, Université Catholique de Louvain, Center for Operations Research and Econometrics (CORE), CORE Discussion Papers 2007076 (Sep. 2007) Google Scholar
  48. 48.
    Nikolova, M.: Local strong homogeneity of a regularized estimator. SIAM J. Appl. Math. 61(2), 633–658 (2000) MATHCrossRefMathSciNetGoogle Scholar
  49. 49.
    Nikolova, M.: Minimizers of cost-functions involving nonsmooth data-fidelity terms. Application to the processing of outliers. SIAM J. Numer. Anal. 40(3), 965–994 (2002) MATHCrossRefMathSciNetGoogle Scholar
  50. 50.
    Nikolova, M.: A variational approach to remove outliers and impulse noise. J. Math. Imag. Vis. 20(1) (2004) Google Scholar
  51. 51.
    Nikolova, M.: Weakly constrained minimization. Application to the estimation of images and signals involving constant regions. J. Math. Imag. Vis. 21(2), 155–175 (2004) CrossRefMathSciNetGoogle Scholar
  52. 52.
    Nikolova, M.: Analysis of the recovery of edges in images and signals by minimizing nonconvex regularized least-squares. SIAM J. Multiscale Model. Simul. 4(3), 960–991 (2005) MATHCrossRefMathSciNetGoogle Scholar
  53. 53.
    Passty, G.B.: Ergodic convergence to a zero of the sum of monotone operators in Hilbert space. J. Math. Anal. Appl. 72 (1979) Google Scholar
  54. 54.
    Pizurica, A., Wink, A.M., Vansteenkiste, E., Philips, W., Roerdink, J.B.T.M.: A review of wavelet denoising in MRI and ultrasound brain imaging. Curr. Med. Imag. Rev. 2(2), 247–260 (2006) CrossRefGoogle Scholar
  55. 55.
    Polyak, B.: Introduction to Optimization. Optimization Software, Inc., Publications Division, New York (1987) Google Scholar
  56. 56.
    Press, W.H., Teukolsky, S.A., Vetterling, W.T., Flannery, B.P.: Numerical Recipes, the Art of Scientific Computing. Cambridge University Press, New York (1992) Google Scholar
  57. 57.
    Rockafellar, R.T.: Monotone operators and the proximal point algorithm. SIAM J. Control Optim. 14(5), 877–898 (1976) MATHCrossRefMathSciNetGoogle Scholar
  58. 58.
    Rudin, L., Osher, S.: Total variation based image restoration with free local constraints. In: Proc. IEEE Int. Conf. on Image Processing, Austin, TX, vol. 1, pp. 31–35 (Nov. 1994) Google Scholar
  59. 59.
    Rudin, L., Lions, P.-L., Osher, S.: In: Osher, S., Paragios, N. (eds.) Multiplicative Denoising and Deblurring: Theory and Algorithms, pp. 103–119. Springer, Berlin (2003) Google Scholar
  60. 60.
    Rudin, L., Osher, S., Fatemi, C.: Nonlinear total variation based noise removal algorithm. Physica D 60, 259–268 (1992) MATHGoogle Scholar
  61. 61.
    Shi, J., Osher, S.: A nonlinear inverse scale space method for a convex multiplicative noise model. SIAM J. Imag. Sci. 1(3), 294–321 (2008) MATHCrossRefMathSciNetGoogle Scholar
  62. 62.
    Simoncelli, E.P.: Bayesian Denoising of Visual Images in the Wavelet Domain. Lecture Notes in Statistics, vol. 41. Springer, Berlin (1999) Google Scholar
  63. 63.
    Simoncelli, E.P., Adelson, E.H.: Noise removal via Bayesian wavelet coding. In: Proc. of the IEEE Int. Conf. on Image Processing, pp. 379–382. Lausanne, Switzerland (Sep. 1996) Google Scholar
  64. 64.
    Tseng, P.: Applications of a splitting algorithm to decomposition in convex programming and variational inequalities. SIAM J. Control Optim. 29(1), 119–138 (1991) MATHCrossRefMathSciNetGoogle Scholar
  65. 65.
    Tseng, P.: A modified forward-backward splitting method for maximal monotone mappings. SIAM J. Control Optim. 38(1), 431–446 (2000) MATHCrossRefMathSciNetGoogle Scholar
  66. 66.
    Tur, M., Chin, C., Goodman, J.W.: When is speckle noise multiplicative? Appl. Opt. 21(7), 1157–1159 (1982) CrossRefGoogle Scholar
  67. 67.
    Ulaby, F., Dobson, M.C.: Handbook of Radar Scattering Statistics for Terrain. Artech House, Norwood (1989) Google Scholar
  68. 68.
    Vogel, C.R., Oman, M.E.: Iterative method for total variation denoising. SIAM J. Sci. Comput. 17(1), 227–238 (1996) MATHCrossRefMathSciNetGoogle Scholar
  69. 69.
    Wang, G., Zhang, J., Pan, G.-W.: Solution of inverse problems in image processing by wavelet expansion. IEEE Trans. Image Process. 4(5), 579–593 (1995) CrossRefGoogle Scholar
  70. 70.
    Weiss, P., Blanc-Féraud, L., Aubert, G.: Efficient schemes for total variation minimization under constraints in image processing. SIAM J. Sci. Comput. 31(3), 2047–2080 (2009) CrossRefMathSciNetGoogle Scholar
  71. 71.
    Xie, H., Pierce, L.E., Ulaby, F.T.: SAR speckle reduction using wavelet denoising and Markov random field modeling. IEEE Trans. Geosci. Remote Sens. 40(10), 2196–2212 (2002) CrossRefGoogle Scholar
  72. 72.
    Yu, Y., Acton, S.T.: Speckle reducing anisotropic diffusion. IEEE Trans. Image Process. 11(11), 1260–1270 (2002) CrossRefMathSciNetGoogle Scholar
  73. 73.
    Zhu, M., Stephen J. Wright, S.J., Chan, T.F.: Duality-based algorithms for total-variation-regularized image restoration. Technical report, CAM 08-33, UCLA (October 2008) Google Scholar

Copyright information

© Springer Science+Business Media, LLC 2009

Authors and Affiliations

  1. 1.M.A.P. 5 (CNRS UMR 8145)Université Paris-Descartes (Paris V)Paris Cedex 06France
  2. 2.GREYC (CNRS UMR 6072)CNRS-ENSICAEN-Universié de CaenCaen CedexFrance
  3. 3.CMLA (CNRS UMR 8536)ENS Cachan, CNRS, PRES UniverSudCachanFrance

Personalised recommendations