×

New splitting algorithms for multiplicative noise removal based on Aubert-Aujol model. (English) Zbl 1513.94005

Summary: In this paper, we propose new algorithms for multiplicative noise removal based on the Aubert-Aujol (AA) model. By introducing a constraint from the forward model with an auxiliary variable for the noise, the NEMA (short for Noise Estimate based Multiplicative noise removal by alternating direction method of multipliers (ADMM)) is firstly given. To further reduce the computational cost, an additional proximal term is considered for the subproblem with regard to the original variable, the \(\mathrm{NEMA}_f\) (short for a variant of NEMA with fully splitting form) is further proposed. We conduct numerous experiments to show the convergence and performance of the proposed algorithms. Namely, the restoration results by the proposed algorithms are better in terms of SNRs for image deblurring than other compared methods including two popular algorithms for AA model and three algorithms of its convex variants.

MSC:

94A08 Image processing (compression, reconstruction, etc.) in information and communication theory
15A29 Inverse problems in linear algebra
65K10 Numerical optimization and variational techniques
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] G. AUBERT AND J. F. AUJOL, A variational approach to removing multiplicative noise, SIAM J. Appl. Math. 68 (2008), 925-946. · Zbl 1151.68713
[2] J. BIEMOND, R. L. LAGENDIJK AND R. M. MERSEREAU, Iterative methods for image deblur-ring, P. IEEE. 78 (1990), 856-883.
[3] J. M. BIOUCAS-DIAS AND M. A. T. FIGUEIREDO, Total variation restoration of speckled images using a split-bregman algorithm, in: Proceedings of the 16th IEEE International Conference on Image Processing, (2009), 3717-3720.
[4] J. M. BIOUCAS-DIAS AND M. A. T. FIGUEIREDO, Multiplicative noise removal using variable splitting and constrained optimization, IEEE T. Image Process. 19 (2010), 1720-1730. · Zbl 1371.94055
[5] S. BOYD, N. PARIKH, E. CHU, B. PELEATO AND J. ECKSTEIN, Distributed optimization and statistical learning via the alternating direction method of multipliers, Found. Trends Mach. Learn. 3 (2011), 1-122. · Zbl 1229.90122
[6] A. CHAMBOLLE AND T. POCK, An introduction to continuous optimization for imaging, Acta Numer. 25 (2016), 161-319. · Zbl 1343.65064
[7] X. J. CHEN, M. K. NG AND C. ZHANG, Non-Lipschitz-regularization and box constrained model for image restoration, IEEE T. Image Process. 21 (2012), 4709-4721. · Zbl 1373.94080
[8] S. DAVID AND F. C. TONY, Edge-preserving and scale-dependent properties of total variation regularization, Inverse Probl. 19 (2003), S165. · Zbl 1043.94512
[9] C. DELEDALLE, L. DENIS, S. TABTI AND F. TUPIN, MuLoG, or how to apply Gaussian de-noisers to multi-channel SAR speckle reduction?, IEEE T. Image Process. 26 (2017), 4389-4403. · Zbl 1409.94107
[10] Y. Q. DONG AND T. Y. ZENG, A convex variational model for restoring blurred images with multiplicative noise, SIAM J. Imaging Sci. 6 (2013), 1598-1625. · Zbl 1283.52012
[11] J. ECKSTEIN AND D. P. BERTSEKAS, On the Douglas-Rachford splitting method and the proximal point algorithm for maximal monotone operators, Math. Program. 55 (1992), 293-318. · Zbl 0765.90073
[12] E. ESSER, X. Q. ZHANG AND T. F. CHAN, A general framework for a class of first order primal-dual algorithms for convex optimization in imaging science, SIAM J. Imaging Sci. 3 (2010), 1015-1046. · Zbl 1206.90117
[13] D. GABAY AND B. MERCIER, A dual algorithm for the solution of nonlinear variational problems via finite element approximation, Comput. Math. Appl. 2 (1976), 17-40. · Zbl 0352.65034
[14] R. GLOWINSKI AND A. MARROCO, Sur l’approximation, paréléments finis d’ordre un, et la résolution, par pénalisation-dualité d’une classe de problèmes de Dirichlet non linéaires, ESAIM: Mathematical Modelling and Numerical Analysis -Modélisation Mathématique et Analyse Numérique 9 (1975), 41-76. · Zbl 0368.65053
[15] D. HAJINEZHAD AND Q. J. SHI, Alternating direction method of multipliers for a class of nonconvex bilinear optimization: convergence analysis and applications, J. Global Optim. 70 (2018), 261-288. · Zbl 1393.90094
[16] Y. M. HUANG, M. K. NG AND Y. W. WEN, A new total variation method for multiplicative noise removal, SIAM J. Imaging Sci. 2 (2009), 20-40. · Zbl 1187.68655
[17] H. A. LE THI, An efficient algorithm for globally minimizing a quadratic function under convex quadratic constraints, Math. Program. 87 (2000), 401-426. · Zbl 0952.90031
[18] H. A. LE THI AND P. TAO, The DC (difference of convex functions) programming and DCA revisited with DC models of real world nonconvex optimization problems, Ann. Oper. Res. 133 (2005), 23-46. · Zbl 1116.90122
[19] F. LI, M. K. NG AND C. M. SHEN, Multiplicative noise removal with spatially varying regu-larization parameters, SIAM J. Imaging Sci. 3 (2010), 1-20. · Zbl 1185.65067
[20] Z. LI, Y. F. LOU AND T. Y. ZENG, Variational multiplicative noise removal by DC program-ming, J. Sci. Comput. 68 (2016), 1200-1216. · Zbl 1350.49047
[21] J. LIU, M. YAN AND T. Y. ZENG, Surface-aware blind image deblurring, IEEE T. Pattern Anal. 43 (2021), 1041-1055.
[22] Y. F. LOU AND M. YAN, Fast ℓ 1 − ℓ 2 minimization via a proximal operator, J. Sci. Comput. 74 (2018), 767-785. · Zbl 1390.90447
[23] Y. F. LOU, T. Y. ZENG, S. OSHER AND J. XIN, A weighted difference of anisotropic and isotropic total variation model for image processing, SIAM J. Imaging Sci. 8 (2015), 1798-1823. · Zbl 1322.94019
[24] Y. F. LOU, X. Q. ZHANG, S. OSHER AND A. BERTOZZI, Image recovery via nonlocal opera-tors, J. Sci. Comput. 42 (2010), 185-197. · Zbl 1203.65088
[25] J. LU, L. X. SHEN, C. XU AND Y. S. XU, Multiplicative noise removal in imaging: An exp-model and its fixed-point proximity algorithm, Appl. Comput. Harmon. A. 41 (2016), 518-539. · Zbl 1360.94043
[26] J. LU, L. X. SHEN, C. XU AND Y. S. XU, Multiplicative noise removal with a sparsity-aware optimization model, Inverse Probl. Imag. 11 (2017), 949-974. · Zbl 1375.94022
[27] M. NIKOLOVA, M. K. NG AND P. TAM, Fast nonconvex nonsmooth minimization methods for image restoration and reconstruction, IEEE T. Image Process. 19 (2010), 3073-3088. · Zbl 1371.94277
[28] P. OCHS, A. DOSOVITSKIY, T. BROX AND T. POCK, An iterated ℓ 1 algorithm for non-smooth non-convex optimization in computer vision, in: Proceedings of the IEEE conference on com-puter vision and pattern recognition, IEEE Computer Society (2013), 1759-1766. · Zbl 1280.90001
[29] C. OLIVER AND S. QUEGAN, Understanding synthetic aperture radar images, SciTech Pub-lishing, (2004).
[30] S. PARRILLI, M. PODERICO, C. V. ANGELINO AND L. VERDOLIVA, A nonlocal SAR image de-noising algorithm based on LLMMSE wavelet shrinkage, IEEE T. Geosci. Remote. 50 (2012), 606-616.
[31] K. PUNITHAKUMAR, J. YUAN, I. B. AYED, S. LI AND Y. BOYKOV, A convex max-flow ap-proach to distribution-based figure-ground separation, SIAM J. Imaging Sci. 5 (2012), 1333-1354. · Zbl 1255.68264
[32] A. REPETTI, E. CHOUZENOUX AND J. PESQUET, A nonconvex regularized approach for phase retrieval, in: IEEE International Conference on Image Processing (ICIP), (2014), 1753-1757.
[33] L. RUDIN, P. L. LIONS AND S. OSHER, Multiplicative denoising and deblurring: theory and algorithms, in: Geometric Level Set Methods in Imaging, Vision and Graphics (2003), 103-119.
[34] L. I. RUDIN, S. OSHER AND E. FATEMI, Nonlinear total variation based noise removal algo-rithms, Physica D. 60 (1992), 259-268. · Zbl 0780.49028
[35] J. M. SCHMITT, S. H. XIANG AND K. M. YUNG, Speckle in optical coherence tomography, J. Biomed. Opt. 4 (1999), 95-105.
[36] J. N. SHI AND S. OSHER, A nonlinear inverse scale space method for a convex multiplicative noise model, SIAM J. Imaging Sci. 1 (2008), 294-321. · Zbl 1185.94018
[37] M. TANG, I. BEN AYED AND Y. BOYKOV, Pseudo-bound optimization for binary energies, in: Computer Vision -ECCV 2014, Springer International Publishing (2014), 691-707.
[38] T. TEUBER AND A. LANG, Nonlocal filters for removing multiplicative noise, in: Scale Space and Variational Methods in Computer Vision, Springer 6667 (2011), 50-61.
[39] R. F. WAGNER, S. W. SMITH, J. M. SANDRIK AND H. LOPEZ, Statistics of speckle in ultra-sound B-scans, IEEE Trans. Sonics Ultrason. 30 (1983), 156-163.
[40] F. WANG AND M. K. NG, A fast minimization method for blur and multiplicative noise removal, Int. J. Comput. Math. 90 (2012), 1-14.
[41] G. WANG, G. T. WANG, Z. PAN AND Z. ZHANG, Multiplicative noise removal using deep CNN denoiser prior, in: 2017 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS), IEEE (2017), 1-6.
[42] Y. WANG, W. T. YIN AND J. S. ZENG, Global convergence of ADMM in nonconvex nonsmooth optimization, J. Sci. Comput. 78 (2019), 29-63. · Zbl 1462.65072
[43] C. L. WU, J. Y. ZHANG AND X. C. TAI, Augmented Lagrangian method for total variation restoration with non-quadratic fidelity, Inverse Probl. Imag. 5 (2011), 237-261. · Zbl 1225.80013
[44] T. T. WU, W. LI, L. H. LI AND T.Y. ZENG, A convex variational approach for image deblur-ring with multiplicative structured noise, IEEE Access. 8 (2020), 37790-37807.
[45] Y. L. WU, Speckle noise removal via nonlocal low-rank regularization, J. Vis. Commun. Image R. 39 (2016), 172-180.
[46] W. J. YAO, Z. C. GUO, J. B. SUN, B. Y. WU AND H. J. GAO, Multiplicative noise removal for texture images based on adaptive anisotropic fractional diffusion equations, SIAM J. Imaging Sci., 12 (2019), 839-873. · Zbl 1524.94037
[47] J. ZHANG, Y. P. DUAN, Y. LU, M. K. NG AND H. B. CHANG, Bilinear constraint based ADMM for mixed Poisson-Gaussian noise removal, Inverse Probl. Imag. 15 (2020), 1-28.
[48] X. L. ZHAO, F. WANG AND M. K. NG, A new convex optimization model for multiplicative noise and blur removal, SIAM J. Imaging Sci. 7 (2014), 456-475. · Zbl 1296.65093
[49] Z. Y. ZHOU, Z. C. GUO, G. DONG, J. B. SUN, D. Z. ZHANG AND B. T. WU, A doubly degenerate diffusion model based on the gray level indicator for multiplicative noise removal, IEEE T. Image Process. 24 (2015), 249-260. · Zbl 1408.94848
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.