Kybernetika 57 no. 3, 446-473, 2021

An algorithm for hybrid regularizers based image restoration with Poisson noise

Cong Thang Pham and Thi Thu Thao TranDOI: 10.14736/kyb-2021-3-0446

Abstract:

In this paper, a hybrid regularizers model for Poissonian image restoration is introduced. We study existence and uniqueness of minimizer for this model. To solve the resulting minimization problem, we employ the alternating minimization method with rigorous convergence guarantee. Numerical results demonstrate the efficiency and stability of the proposed method for suppressing Poisson noise.

Keywords:

total variation, image denoising, image deblurring, alternating minimization method

Classification:

35A15, 94A08

paper.pdf

References:

  1. G. Aubert and P. Kornprobst: Mathematical Problems in Image Processing: partial differential equations and the calculus of variations. (Second edition) Applied Mathematical Science 147, Springer-Verlag, New York 2006.   DOI:
  2. J. M. Bardsley and J. Goldes: Techniques for regularization parameter and hyper-parameter selection in PET and SPECT imaging. Inverse Probl. Sci. Engrg. 19 (2011), 2, 267-280.   DOI:10.1080/17415977.2010.550048
  3. S. Boyd, N. Parikh and et al.: Distributed optimization and statistical learning via the alternating direction method of multipliers Found. Trends Mach. Learn. 3 (2010), 1-122.   CrossRef
  4. A. C. Bovik and Z. Wang: Modern Image Quality Assessment, Synthesis Lectures on Image, Video, and Multimedia Processing. Morgan and Claypool Publishers, 2006.   DOI:10.2200/s00010ed1v01y200508ivm003
  5. R. H. Chan and K. Chen: Multilevel algorithm for a Poisson noise removal model with total-variation regularization. Int. J. Comput. Math. 84 (2007), 8, 1183-1198.   DOI:10.1080/00207160701450390
  6. D. Q. Chen and L. Z. Cheng: Deconvolving Poissonian images by a novel hybrid variational model. J. Vis. Commun. Image R. 22 (2011), 7, 643-652.   DOI:10.1016/j.jvcir.2011.07.007
  7. Y. M. Chen and T. Wunderli: Adaptive total variation for image restoration in BV space. J. Math. Anal. Appl. 272 (2002), 1, 117-137.   DOI:10.1016/s0022-247x(02)00141-5
  8. F. X. Dupe, M. J. Fadili and J L. Starck: Deconvolution of confocal microscopy images using proximal iteration and sparse representations. In: I. S. Biomed. Imaging, Paris, France (2008), pp. 736-739.   CrossRef
  9. I. Ekeland and R. Temam: Convex Analysis and Variational Problems. Classics in Applied Mathematics, SIAM 1999.   CrossRef
  10. J. Eckstein and D. P. Bertsekas: On the Douglas-Rachford splitting method and the proximal point algorithm for maximal monotone operators. Math. Programming 55 (1992), 293-318.   DOI:10.1007/BF01581204
  11. I. Frosioa and N. A. Borghese: Compression and smart coding of offset and gain maps for intraoral digital x-ray sensors. Med. Phys. 36 (2009), 2, 464-479.   DOI:10.1118/1.3050159
  12. C. He, C. Hu, W. Zhang and B. Shi: A fast adaptive parameter estimation for total variation image restoration. IEEE Trans. Image Process. 23 (2014), 12, 4954-4967.   DOI:10.1109/TIP.2014.2360133
  13. L. Jiang, J. Huang, X. G. Lv and J. Liu: Restoring Poissonian images by a combined first-order and second-order variation approach. J. Math. 2013 (2013), 274573.   DOI:10.1155/2013/274573
  14. L. Jiang, J. Huang, X. G. Lv and J. Liu: Alternating direction method for the high-order total variation-based Poisson noise removal problem. Numer. Algorithms 69 (2015), 3, 495-516.   DOI:10.1007/s11075-014-9908-y
  15. T. Le, R. Chartrand and T. Asaki: A variational approach to constructing images corrupted by Poisson noise. J. Math. Imaging Vis. 27 (2007), 257-263.   DOI:10.1007/s10851-007-0652-y
  16. F. Li, C. M. Shen, J. S. Fan and C. L. Shen: Image restoration combining a total variational filter and a fourth-order filter. J. Vis. Commun. Image Res. 18 (2007), 4, 322-330.   DOI:10.1016/j.jvcir.2007.04.005
  17. Q. Liu, Z. Yao and Y. Ke: Entropy solutions for a fourth-order nonlinear degenerate problem for noise removal. Nonlinear Anal. Theor. 67 (2007), 6, 1908-1918.   DOI:10.1016/j.na.2006.08.016
  18. X. Liu: Augmented Lagrangian method for total generalized variation based Poissonian image restoration. Comput. Math. Appl. 71 (2016), 8, 1694-1705.   DOI:10.1016/j.camwa.2016.03.005
  19. X. Liu and L. Huang: Total bounded variation-based Poissonian images recovery by split Bregman iteration. Math. Methods Appl. Sci. 35, (2012), 5, 520-529.   DOI:10.1002/mma.1588
  20. X. Liu and L. Huang: Poissonian image reconstruction using alternating direction algorithm. J. Electronic Imaging 22 (2013), 3, 033007.   DOI:10.1117/1.JEI.22.3.033007
  21. X. G. Lv, L. Jiang and J. Liu: Deblurring Poisson noisy images by total variation with overlapping group sparsity. Appl. Math. Comput. 289 (2016), 20, 132-148.   DOI:10.1016/j.amc.2016.03.029
  22. M. Ma, J. Zhang and et al.: Adaptive image restoration via a relaxed regularization of mean curvature. Math. Probl. Eng. (2020), 3416907.   DOI:10.1155/2020/3416907
  23. C. A. Micchelli, L. Shen and Y. Xu: Proximity algorithms for image models: denoising. Inverse Probl. 27 (2011), 4, 045009.   DOI:10.1088/0266-5611/27/4/045009
  24. S. Osher and O. Scherzer: G-norm properties of bounded variation regularization. Commun. Math. Sci. 2 (2004), 2, 237-254.   DOI:10.4310/cms.2004.v2.n2.a6
  25. A. Padcharoen, P. Kumama and J. Martinez-Moreno: Augmented Lagrangian method for TV-$l$1-$l$2 based colour image restoration. J. Comput. Appl. Math.354 (2019), 507-519.   DOI:10.1016/j.cam.2018.09.053
  26. C. T. Pham and A. Kopylov: Multi-quadratic dynamic programming procedure of edge-preserving denoising for medical images. Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci. XL-5/W6 (2015), 101-106.   DOI:10.5194/isprsarchives-XL-5-W6-101-2015
  27. C. T. Pham, G. Gamard, A. Kopylov and T. T. T. Tran: An algorithm for image restoration with mixed noise using total variation regularization. Turk. J. Elec. Eng. Comp. Sci. 26 (2018), 2832-2846.   DOI:10.3906/elk-1803-100
  28. C. T. Pham and A. V. Kopylov: Tree-serial parametric dynamic programming with flexible prior model for image denoising. Comput. Opt. 42 (2018), 838-845.   DOI:10.1002/gepi.22154
  29. C. T. Pham, T. T. T. Tran and et. al.: An adaptive algorithm for restoring image corrupted by mixed noise. Cybern. Phys. 8 (2019), 73-82.   DOI:10.35470/2226-4116-2019-8-2-73-82
  30. C. T. Pham, T. T. T. Tran and G. Gamard: An efficient total variation minimization method for image restoration. Informatica 31 (2020), 539-560.   DOI:10.15388/20-infor407
  31. P. Sarder and A. Nehorai: Deconvolution method for 3D fluorescence microscopy images. IEEE Signal Process. Magazine 23 (2006), 3, 32-45.   DOI:10.1109/MSP.2006.1628876
  32. A. Sawatzky, C. Brune, T. Kasters, F. Wabbeling and M. Burger: EM-TV methods for inverse problems with Poisson noise. Lect. Notes Math. Springer 2090 (2013), 71-142.   DOI:10.1007/978-3-319-01712-9\_2
  33. S. Setzer, G. Steidl and T. Teuber: Deblurring Poissonian images by split Bregman techniques. J. Vis. Commun. Image R. 21 (2010), 3, 193-199.   DOI:10.1016/j.jvcir.2009.10.006
  34. M. Yan: EM-type algorithms for image reconstruction with background emission and Poisson noise. Lect. Notes Comput. Sci. Springer Berlin Heidelberg 6938 (2011), 33-42.   DOI:10.1007/978-3-642-24028-7\_4
  35. J. Zhang, M. Ma, Z. Wu and C. Deng: High-order total bounded variation model and its fast algorithm for poissonian image restoration. Math. Probl. Engrg. (2019), 2502731.   DOI:10.1155/2019/2502731
  36. Y. Wang, J. Yang, W. Yin and Y. Zhang: A new alternating minimization algorithm for total variation image reconstruction. SIAM J. Imaging Sci. 1 (2008), 3, 248-272.   DOI:10.1137/080724265
  37. Y. Wen, R. H. Chan and T. Zeng: Primal-dual algorithms for total variation based image restoration under Poisson noise. Sci. China Math. 59 (2016), 141-160.   DOI:10.1007/s11425-015-5079-0
  38. H. Woo and S. Yun: Alternating minimization algorithm for speckle reduction with a shifting technique. IEEE T. Image Process. 21 (2012), 1701-1714.   DOI:10.1109/TIP.2011.2176345