[go: up one dir, main page]
More Web Proxy on the site http://driver.im/ Skip to main content
Springer Nature Link
Log in

Deep CNN Denoiser prior for multiplicative noise removal

  • Published:
Multimedia Tools and Applications Aims and scope Submit manuscript

Abstract

Multiplicative noise removal is always a hard problem in fundamental image processing task. Many methods are proposed for the multiplicative noise removal by using different denoiser prior in variational framework. Among the image prior, total variation (TV) is first proposed and then many other regularization such as PM, TGV, nonlocal and many other priors are also proposed for enhancing the denoising ability. Although using the priors can get good performance, the models are hard to be resolved with sophisticated priors. A new model based on the deep CNN denoiser prior for removing multiplicative noise is proposed in this paper. The proposed energy function is easy calculated via several sub-optimal questions by split bregman method and alternative minimization is used for the solution. The proposed method does not need to deduce the sophisticated formula and can achieve good performance. From the experiments, we can see that our method achieved good results.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
£29.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price includes VAT (United Kingdom)

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3

Similar content being viewed by others

References

  1. Afonso M, Miguel Sanches J (2015) Image reconstruction under multiplicative speckle noise using total variation. Neurocomputing 150(2):200–213

    Article  Google Scholar 

  2. Aubert G, Aujol J (2008) A variational approach to remove multiplicative noise. SIAM J Appl Math 68(4):925–946

    Article  MathSciNet  MATH  Google Scholar 

  3. Chen Y, Pock T (2017) Trainable nonlinear reaction diffusion: a flexible framework for fast and effective image restoration. IEEE Trans Pattern Anal Mach Intell 39(6):1256–1272

    Article  Google Scholar 

  4. Dabov K, Foi A, Katkovnik V, Egiazarian K (2007) Image denoising by sparse 3-D transform-domain collaborative filtering. IEEE Trans Image Process 16(8):2080–2095

    Article  MathSciNet  Google Scholar 

  5. Denis L, Tupin F, Darbon J, Sigelle M (2009) SAR image regularization with fast approximate discrete minimization. IEEE Trans Image Process 18(7):1588–1600

    Article  MathSciNet  MATH  Google Scholar 

  6. Dong J, Han Z, Zhao Y et al (2017) Sparse analysis model based multiplicative noise removal with enhanced regularization. Signal Process 137(8):160–176

    Article  Google Scholar 

  7. Duan JM, Pan ZK, Zhang BC, Liu WQ, Tai X-C (2015) Fast algorithm for color texture image inpainting using the non-local ctv model. J Glob Optim 62(4):853–876

    Article  MathSciNet  MATH  Google Scholar 

  8. Gu S, Zhang L, Zuo W, Feng X (2014) Weighted nuclear norm minimization with application to image denoising. In: IEEE Conference on Computer Vision and Pattern Recognition, pp 2862–2869

  9. Hao Y, Xu J, Li S, Zhang X (2015) A variational model based on split Bregman method for multiplicativenoise removal. AEU - Int J Electron C 69(9):1291–1296

    Article  Google Scholar 

  10. Huang YM, Ng MK, Wen YW (2009) A new total variation method for multiplicative noise removal. SIAM J Imaging Sci 2(1):20–40

    Article  MathSciNet  MATH  Google Scholar 

  11. Jian M, Lam KM, Dong J et al (2015) Visual-patch-attention-aware saliency detection. IEEE T Cybernetics 45(8):1575–1586

    Article  Google Scholar 

  12. Jian M, Qi Q, Dong J et al (2017) Saliency detection using quaternionic distance based weber local descriptor and level priors. Multimed Tools Appl 76(11):1–17

    Google Scholar 

  13. Li S, Wang G, Zhao X (2016) Multiplicative noise removal via adaptive learned dictionaries and TV regularization. Digit Signal Process 50(3):218–228

    Article  Google Scholar 

  14. Liu M, Fan Q (2016) A modified convex variational model for multiplicative noiseremoval. J Vis Commun Image Represent 36(4):187–198

    Article  Google Scholar 

  15. Liu P, Xiao L (2015) Efficient multiplicative noise removal method using isotropic second order total variation. Comput Math Appl 70(8):2029–2048

    Article  MathSciNet  Google Scholar 

  16. Liu WQ, Duan JM, Qiu ZW et al (2016) Implementation of high-order variational models made easy for image processing. Math Method Appl Sci 39(14):4208–4233

    Article  MathSciNet  MATH  Google Scholar 

  17. Lu DY (2016) A hybrid optimization method for multiplicative noise and blur removal. J Comput Appl Math 302(15):224–233

    Article  MathSciNet  MATH  Google Scholar 

  18. Lu J, Wang G, Pan Z (2017) Nonlocal active contour model for texture segmentation. Multimedia Tools and Applications 76(8):10991–11001

    Article  Google Scholar 

  19. Lv XG, Le J, Huang J et al (2013) A fast high-order total variation minimization method for multiplicative noise removal. Math Probl Eng 2013(1-4):87–118

    MathSciNet  Google Scholar 

  20. Lysaker M, Lundervold A, Tai XC (2003) Noise removal using fourth-order partial differential equation with applications to medical magnetic resonance images in space and time. IEEE Trans Image Process 12(12):1579–1590

    Article  MATH  Google Scholar 

  21. Perona P, Malik J (1990) Scale space and edge detection using anisotropic diffusion. IEEE Trans Pattern Anal Mach Intell 12:629–639

    Article  Google Scholar 

  22. Rudin LI, Osher S, Fatemi E (1992) Nonlinear total variation based noise removal algorithms. Physica D 60(1-4):259–268

    Article  MathSciNet  MATH  Google Scholar 

  23. Rudin L, Lions P, Osher S (2003) Multiplicative denoising and deblurring: theory and algorithms. In: Osher S, Paragios N (eds) Geometric level set methods in imaging, vision and graphics. Springer, pp 103–119

  24. Setzer S, Steidl G, Teuber T (2010) Deblurring Poissonian images by split Bregman techniques. J Vis Commun Image Represent 21(3):193–199

    Article  Google Scholar 

  25. Shama M, Huang T, Liu J, Wang S (2016) A convex total generalized variation regularized model for multiplicativenoise and blur removal. Appl Math Comput 276(5):109–121

    MATH  Google Scholar 

  26. Shi JN, Osher S (2008) A nonlinear inverse scale space method for a convex multiplicative noise model. Siam J Imaging Sci 1(3):294–321

    Article  MathSciNet  MATH  Google Scholar 

  27. Ullah A, Chen W, Sun H, Khan MA (2016) A modified multi-grid algorithm for a novel variational model to removemultiplicative noise. J Vis Commun Image Represent 40(Part B):485–501

    Article  Google Scholar 

  28. Ullah A, Chen W, Khan MA (2016) A new variational approach for restoring images with multiplicative noise. Comput Math Appl 71(10):2034–2050

    Article  MathSciNet  Google Scholar 

  29. Wang CP, Pan ZK, Zhang ZM et al (2010) A general variational model for multiplicative noise removal and its split Bregman algorithm. International Congress on Image and Signal Processing. IEEE, pp 571–577

  30. Wang G, Pan Z, Zhang W, Dong Q Multiplicative noise removing using sparse prior regulization. 2013 IEEE 6th International Conference on Image and Signal Processing (CISP), 281–285, Hangzhou, China, December 26-28, 2013

  31. Wang G, Lu J, Pan Z (2017) Color texture segmentation based on active contour model with multichannel nonlocal and Tikhonov regularization. Multimed Tools Appl 76(22):24515–24526

    Article  Google Scholar 

  32. Zhang K, Zuo W, Gu S, Zhang L (2017) Learning deep CNN Denoiser prior for image restoration. CVPR

Download references

Acknowledgments

This work was supported by the National Natural Science Foundation of China (No.61772294), The National Scientific and Technological Development and Planning Project during the Twelfth Five-year Plan Period (No.2014BAG03B05).

Author information

Authors and Affiliations

  1. College of Computer Science and Technology, Qingdao University, Qingdao, China

    Guodong Wang & Zhenkuan Pan

  2. College of Data Science and Software Engineering, Qingdao University, Qingdao, China

    Zhimei Zhang

Authors
  1. Guodong Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Zhenkuan Pan
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Zhimei Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Guodong Wang.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Wang, G., Pan, Z. & Zhang, Z. Deep CNN Denoiser prior for multiplicative noise removal. Multimed Tools Appl 78, 29007–29019 (2019). https://doi.org/10.1007/s11042-018-6294-9

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-018-6294-9

Keywords

Search

Navigation