Advertisement

Adaptive Regularization for Image Reconstruction from Subsampled Data

  • Michael HintermüllerEmail author
  • Andreas Langer
  • Carlos N. Rautenberg
  • Tao Wu
Conference paper
Part of the Mathematics and Visualization book series (MATHVISUAL)

Abstract

Choices of regularization parameters are central to variational methods for image restoration . In this paper, a spatially adaptive (or distributed) regularization scheme is developed based on localized residuals, which properly balances the regularization weight between regions containing image details and homogeneous regions. Surrogate iterative methods are employed to handle given subsampled data in transformed domains, such as Fourier or wavelet data. In this respect, this work extends the spatially variant regularization technique previously established in Dong et al. (J Math Imaging Vis 40:82–104, 2011), which depends on the fact that the given data are degraded images only. Numerical experiments for the reconstruction from partial Fourier data and for wavelet inpainting prove the efficiency of the newly proposed approach.

Notes

Acknowledgements

This research was supported by the Austrian Science Fund (FWF) through START-Project Y305 “Interfaces and Free Boundaries” and SFB-Project F3204 “Mathematical Optimization and Applications in Biomedical Sciences”, the German Research Foundation DFG through Project HI1466/7-1 “Free Boundary Problems and Level Set Methods”, as well as the Research Center MATHEON through Project C-SE15 “Optimal Network Sensor Placement for Energy Efficiency” supported by the Einstein Center for Mathematics Berlin.

References

  1. 1.
    A. Almansa, C. Ballester, V. Caselles, G. Haro, A TV based restoration model with local constraints. J. Sci. Comput. 34, 209–236 (2008)MathSciNetCrossRefGoogle Scholar
  2. 2.
    M. Bertalmio, V. Caselles, B. Rougé, A. Solé, TV based image restoration with local constraints. J. Sci. Comput. 19, 95–122 (2003)MathSciNetCrossRefGoogle Scholar
  3. 3.
    A. Bovik, Handbook of Image and Video Processing (Academic, San Diego, 2000)zbMATHGoogle Scholar
  4. 4.
    A. Buades, B. Coll, J.-M. Morel, A review of image denoising algorithms, with a new one. Multiscale Model. Simul. 4, 490–530 (2005)MathSciNetCrossRefGoogle Scholar
  5. 5.
    A. Chambolle, An algorithm for total variation minimization and applications. J. Math. Imaging Vision 20, 89–97 (2004)MathSciNetCrossRefGoogle Scholar
  6. 6.
    A. Chambolle, P.-L. Lions, Image recovery via total variation minimization and related problems. Numer. Math. 76, 167–188 (1997)MathSciNetCrossRefGoogle Scholar
  7. 7.
    T.F. Chan, J. Shen, H.-M. Zhou, Total variation wavelet inpainting. J. Math. Imaging Vision 25, 107–125 (2006)MathSciNetCrossRefGoogle Scholar
  8. 8.
    Q. Chang, I.-L. Chern, Acceleration methods for total variation based image denoising. SIAM J. Appl. Math. 25, 982–994 (2003)MathSciNetzbMATHGoogle Scholar
  9. 9.
    Q. Chen, P. Montesinos, Q.S. Sun, P.A. Heng, D.S. Xia, Adaptive total variation denoising based on difference curvature. Image Vis. Comput. 28, 298–306 (2010)CrossRefGoogle Scholar
  10. 10.
    K. Chen, E.L. Piccolomini, F. Zama, An automatic regularization parameter selection algorithm in the total variation model for image deblurring. Numer. Algorithms 67, 73–92 (2014)MathSciNetCrossRefGoogle Scholar
  11. 11.
    I. Daubechies, Ten Lectures on Wavelets (SIAM, Philadelphia, 1992)CrossRefGoogle Scholar
  12. 12.
    I. Daubechies, M. Defrise, C. De Mol, An iterative thresholding algorithm for linear inverse problems with a sparsity constraint. Commun. Pure Appl. Math. 57, 1413–1457 (2004)MathSciNetCrossRefGoogle Scholar
  13. 13.
    I. Daubechies, G. Teschke, L. Vese, Iteratively solving linear inverse problems under general convex constraints. Inverse Prob. Imaging 1, 29–46 (2007)MathSciNetCrossRefGoogle Scholar
  14. 14.
    D.C. Dobson, C.R. Vogel, Convergence of an iterative method for total variation denoising. SIAM J. Numer. Anal. 34, 1779–1791 (1997)MathSciNetCrossRefGoogle Scholar
  15. 15.
    Y. Dong, M. Hintermüller, M. Rincon-Camacho, Automated regularization parameter selection in multi-scale total variation models for image restoration. J. Math. Imaging Vis. 40, 82–104 (2011)MathSciNetCrossRefGoogle Scholar
  16. 16.
    K. Frick, P. Marnitz, Statistical multiresolution Dantzig estimation in imaging: fundamental concepts and algorithmic framework. Electron. J. Stat. 6, 231–268 (2012)MathSciNetCrossRefGoogle Scholar
  17. 17.
    K. Frick, P. Marnitz, A. Munk, Statistical multiresolution estimation for variational imaging: with an application in Poisson-biophotonics. J. Math. Imaging Vision 46, 370–387 (2013)MathSciNetCrossRefGoogle Scholar
  18. 18.
    R. Giryes, M. Elad, Y.C. Eldar, The projected GSURE for automatic parameter tuning in iterative shrinkage methods. Appl. Comput. Harmon. Anal. 30, 407–422 (2011)MathSciNetCrossRefGoogle Scholar
  19. 19.
    T. Goldstein, S. Osher, The split Bregman method for 1 regularized problems. SIAM J. Imaging Sci. 2, 1311–1333 (2009)MathSciNetCrossRefGoogle Scholar
  20. 20.
    C. He, C. Hu, W. Zhang, B. Shi, A fast adaptive parameter estimation for total variation image restoration. IEEE Trans. Image Process. 23, 4954–4967 (2014)MathSciNetCrossRefGoogle Scholar
  21. 21.
    M. Hintermüller, K. Kunisch, Total bounded variation regularization as bilaterally constrained optimization problem. SIAM J. Appl. Math. 64, 1311–1333 (2004)MathSciNetCrossRefGoogle Scholar
  22. 22.
    M. Hintermüller, C.N. Rautenberg, Optimal selection of the regularization function in a weighted total variation model. Part I: modelling and theory. J. Math. Imaging Vision 59(3), 498–514 (2017)zbMATHGoogle Scholar
  23. 23.
    M. Hintermüller, M.M. Rincon-Camacho, Expected absolute value estimators for a spatially adapted regularization parameter choice rule in L 1-TV-based image restoration. Inverse Prob. 26, 085005 (2010)MathSciNetCrossRefGoogle Scholar
  24. 24.
    M. Hintermüller, G. Stadler, An infeasible primal-dual algorithm for total bounded variation-based Inf-convolution-type image restoration. SIAM J. Sci. Comput. 28, 1–23 (2006)MathSciNetCrossRefGoogle Scholar
  25. 25.
    M. Hintermüller, C.N. Rautenberg, T. Wu, A. Langer, Optimal selection of the regularization function in a weighted total variation model. Part II: algorithm, its analysis and numerical tests. J. Math. Imaging Vision 59(3), 515–533 (2017)MathSciNetCrossRefGoogle Scholar
  26. 26.
    T. Hotz, P. Marnitz, R. Stichtenoth, L. Davies, Z. Kabluchko, A. Munk, Locally adaptive image denoising by a statistical multiresolution criterion. Comput. Stat. Data Anal. 56(33), 543–558 (2012)MathSciNetzbMATHGoogle Scholar
  27. 27.
    F. Lenzen, F. Becker, J. Lellmann, S. Petra, C. Schnörr, A class of quasi-variational inequalities for adaptive image denoising and decomposition. Comput. Optim. Appl. 54, 371–398 (2013)MathSciNetCrossRefGoogle Scholar
  28. 28.
    F. Lenzen, J. Lellmann, F. Becker, C. Schnörr, Solving quasi-variational inequalities for image restoration with adaptive constraint sets. SIAM J. Imaging Sci. 7, 2139–2174 (2014)MathSciNetCrossRefGoogle Scholar
  29. 29.
    S. Osher, M. Burger, D. Goldfarb, J. Xu, W. Yin, An iterative regularization method for total variation-based image restoration. Multiscale Model. Simul. 4, 460–489 (2005)MathSciNetCrossRefGoogle Scholar
  30. 30.
    Y. Ruan, H. Fang, Q. Chen, Semiblind image deconvolution with spatially adaptive total variation regularization. Math. Probl. Eng. 2014(606170), 8 (2014)Google Scholar
  31. 31.
    L.I. Rudin, S. Osher, E. Fatemi, Nonlinear total variation based noise removal algorithms. Physica D 60, 259–268 (1992)MathSciNetCrossRefGoogle Scholar
  32. 32.
    D. Strong, T. Chan, Spatially and scale adaptive total variation based regularization and anisotropic diffusion in image processing. Technical report, UCLA (1996)Google Scholar
  33. 33.
    D. Strong, T. Chan, Edge-preserving and scale-dependent properties of total variation regularization. Inverse Prob. 19, 165–187 (2003)MathSciNetCrossRefGoogle Scholar
  34. 34.
    D. Strong, J.-F. Aujol, T. Chan, Scale recognition, regularization parameter selection, and Meyer’s G norm in total variation regularization. Technical report, UCLA (2005)Google Scholar
  35. 35.
    C. Sutour, C.-A. Deledalle, J.-F. Aujol, Adaptive regularization of the NL-means: application to image and video denoising. IEEE Trans. Image Process. 23, 3506–3521 (2014)MathSciNetCrossRefGoogle Scholar
  36. 36.
    E. Tadmor, S. Nezzar, L. Vese, A multiscale image representation using hierarchical (BV, L 2) decompositions. Multiscale Moel. Simul. 2, 554–579 (2004)MathSciNetCrossRefGoogle Scholar
  37. 37.
    E. Tadmor, S. Nezzar, L. Vese, Multiscale hierarchical decomposition of images with applications to deblurring, denoising and segmentation. Commun. Math. Sci. 6, 1–26 (2008)MathSciNetCrossRefGoogle Scholar
  38. 38.
    C.R. Vogel, Computational Methods for Inverse Problems. Frontiers in Applied Mathematics, vol. 23 (SIAM, Philadelphia, 2002)Google Scholar
  39. 39.
    Z. Wang, A.C. Bovik, H.R. Sheikh, E.P. Simoncelli, Image quality assessment: from error to structural similarity. IEEE Trans. Image Process. 13, 600–612 (2004)CrossRefGoogle Scholar
  40. 40.
    Y.-W. Wen, R.H. Chan, Parameter selection for total -variation-based image restoration using discrepancy principle. IEEE Trans. Image Process. 21, 1770–1781 (2012)MathSciNetCrossRefGoogle Scholar
  41. 41.
    L. Yan, H. Fang, S. Zhong, Blind image deconvolution with spatially adaptive total variation regularization. Opt. Lett. 37, 2778–2780 (2012)CrossRefGoogle Scholar
  42. 42.
    Q. Yuan, L. Zhang, H. Shen, Multiframe super-resolution employing a spatially weighted total variation model. IEEE Trans. Circuits Syst. Video Technol. 22, 379–392 (2012)CrossRefGoogle Scholar
  43. 43.
    Q. Yuan, L. Zhang, H. Shen, Regional spatially adaptive total variation super-resolution with spatial information filtering and clustering. IEEE Trans. Image Process. 22, 2327–2342 (2013)MathSciNetCrossRefGoogle Scholar
  44. 44.
    X. Zhang, T.F. Chan, Wavelet inpainting by nonlocal total variation. Inverse Prob. Imaging 4, 191–210 (2010)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG, part of Springer Nature 2018

Authors and Affiliations

  • Michael Hintermüller
    • 1
    Email author
  • Andreas Langer
    • 2
  • Carlos N. Rautenberg
    • 3
  • Tao Wu
    • 4
  1. 1.Weierstrass InstituteBerlinGermany
  2. 2.Universität StuttgartStuttgartGermany
  3. 3.Humboldt-Universität zu BerlinBerlinGermany
  4. 4.Technische Universität MünchenGarchingGermany

Personalised recommendations