Neural Computing and Applications

, Volume 31, Supplement 1, pp 325–336 | Cite as

An improved image mixed noise removal algorithm based on super-resolution algorithm and CNN

  • Ling Ding
  • Huyin ZhangEmail author
  • Jinsheng Xiao
  • Bijun Li
  • Shejie Lu
  • Mohammad Norouzifard
Machine Learning Applications for Self-Organized Wireless Networks


Based on the hardware and sensors of image acquisition, the noise in the image has been easily generated. In this paper, an improved method of image decompression has proposed the shortcoming of the above-mentioned hardware algorithm. The traditional filter desiccation algorithm can only remove one or two specific noises, and it is not effective for other types. We combine some excellent neural network models. In this paper, an image mixing noise removal algorithm based on convolution nerve has been mentioned. Aiming at realizing the super-resolution of the image, the deconvolution layer can be used only to enlarge the image. The magnification factor is the step of deconvolution. This paper aims to eliminate the interference of the image noise. The effect of magnification on the deconvolution layer is impossible. The results of experimental test show that the algorithm achieves a good noise removal effect and is suitable for various mixed noise images. The algorithm used in this paper improves the subjective visual effect and objective evaluation index.


Hardware Filter desiccation algorithm Deconvolution layer 



This paper is funded by the National Natural Science Foundation of China (Project Nos. 41671441, 61540059, and 91120002); the Plan Project of Guangdong Provincial Science and Technology (Project No. 2015B010131007); Hubei Provincial Department of Education Guiding Project (B2016187); and Joint Fund Project (NSFC—Guangdong Big Data Science Center Project), Project No. U1611262.


  1. 1.
    Loncan L et al (2015) Hyperspectral pansharpening: a review. IEEE Geosci Remote Sens Mag 3(3):27–46CrossRefGoogle Scholar
  2. 2.
    Polatkan G et al (2015) A Bayesian nonparametric approach to image super-resolution. IEEE Trans Pattern Anal Mach Intell 37(2):346–358CrossRefGoogle Scholar
  3. 3.
    Patel RC, Joshi MV (2015) Super-resolution of hyperspectral images: use of optimum wavelet filter coefficients and sparsity regularization. IEEE Trans Geosci Remote Sens 53(4):1728–1736CrossRefGoogle Scholar
  4. 4.
    Simões M et al (2015) A convex formulation for hyperspectral image superresolution via subspace-based regularization. IEEE Trans Geosci Remote Sens 53(6):3373–3388CrossRefGoogle Scholar
  5. 5.
    Hell SW et al (2015) The 2015 super-resolution microscopy roadmap. J Phys D Appl Phys 48(44):443001CrossRefGoogle Scholar
  6. 6.
    Nguyen A et al (2016) Plug and play generative networks: conditional iterative generation of images in latent space. arXiv preprint arXiv:1612.00005
  7. 7.
    Li C, Wand M (2016) Precomputed real-time texture synthesis with markovian generative adversarial networks. European conference on computer vision. Springer, Cham, pp 702–716Google Scholar
  8. 8.
    J Flynn et al (2016) Deepstereo: learning to predict new views from the world’s imagery. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 5515–5524Google Scholar
  9. 9.
    Deng C et al (2016) Similarity constraints-based structured output regression machine: an approach to image super-resolution. IEEE Trans Neural Netw Learn Syst 27(12):2472–2485CrossRefGoogle Scholar
  10. 10.
    Juefei-Xu F et al (2016) Deepgender: occlusion and low resolution robust facial gender classification via progressively trained convolutional neural networks with attention. In: Proceedings of the IEEE conference on computer vision and pattern recognition workshops, pp 68–77Google Scholar
  11. 11.
    Jiang J, Zhang L, Yang J (2014) Mixed noise removal by weighted encoding with sparse nonlocal regularization. IEEE Trans Image Process 23(6):2651–2662MathSciNetCrossRefzbMATHGoogle Scholar
  12. 12.
    Rudin LI, Osher S, Fatemi E (1992) Nonlinear total variation based noise removal algorithms. Phys D Nonlinear Phenom 60(1–4):259–268MathSciNetCrossRefzbMATHGoogle Scholar
  13. 13.
    Aharon M, Elad M, Bruckstein A (2006) K-SVD: an algorithm for designing over complete dictionaries for sparse representation. IEEE Trans Signal Process 54(11):4311–4322CrossRefzbMATHGoogle Scholar
  14. 14.
    Dabov K, Foi A, Katkovnik V et al (2007) Image denoising by sparse 3-D transform-domain collaborative filtering. IEEE Trans Image Process 16(8):2080–2095MathSciNetCrossRefGoogle Scholar
  15. 15.
    Knaus C, Zwicker M (2013) Dual-domain image denoising. In: 2013 20th IEEE international conference on image processing (ICIP). IEEE, pp 440–444Google Scholar
  16. 16.
    Xiao J, Li W, Jiang H, Peng H, Zhu S (2015) Three dimensional block-matching video denoising algorithm based on dual-domain filtering. J Commun 9:91–97Google Scholar
  17. 17.
    Chen T, Wu HR (2001) Space variant median filters for the restoration of impulse noise corrupted images. IEEE Trans Circuits Syst II Analog Digital Signal Process 48(8):784–789CrossRefzbMATHGoogle Scholar
  18. 18.
    Ko SJ, Lee YH (1991) Center weighted median filters and their applications to image enhancement. IEEE Trans Circuits Syst 38(9):984–993CrossRefGoogle Scholar
  19. 19.
    Hwang H, Haddad RA (1995) Adaptive median filters: new algorithms and results. IEEE Trans Image Process 4(4):499–502CrossRefGoogle Scholar
  20. 20.
    Cai JF, Chan RH, Nikolova M (2010) Fast two-phase image deblurring under impulse noise. J Math Imaging Vis 36(1):46–53MathSciNetCrossRefGoogle Scholar
  21. 21.
    Mitra K, Veeraraghavan A, Chellappa R (2010) Robust RVM regression using sparse outlier model. In: 2010 IEEE conference on computer vision and pattern recognition (CVPR). IEEE, pp 1887–1894Google Scholar
  22. 22.
    Liu W et al (2017) A survey of deep neural network architectures and their applications. Neurocomputing 234:11–26CrossRefGoogle Scholar
  23. 23.
    Yu K et al (2018) Crafting a Toolchain for image restoration by deep reinforcement learning. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2443–2452Google Scholar
  24. 24.
    Chen H et al (2017) Low-dose CT with a residual encoder-decoder convolutional neural network. IEEE Trans Med Imaging 36(12):2524–2535CrossRefGoogle Scholar
  25. 25.
    Mei S, Yuan X, Ji J et al (2017) Hyperspectral image spatial super-resolution via 3D full convolutional neural network. Remote Sens 9(11):1139CrossRefGoogle Scholar
  26. 26.
    Hou W et al (2015) Blind image quality assessment via deep learning. IEEE Trans Neural Netw Learn Syst 26(6):1275–1286MathSciNetCrossRefGoogle Scholar
  27. 27.
    Aggarwal HK, Majumdar A (2016) Hyperspectral image denoising using spatio-spectral total variation. IEEE Geosci Remote Sens Lett 13(3):442–446Google Scholar
  28. 28.
    Burger HC, Schuler CJ, Harmeling S (2012) Image denoising: can plain neural networks compete with BM3D? In: 2012 IEEE conference on computer vision and pattern recognition (CVPR). IEEE, pp 2392–2399Google Scholar
  29. 29.
    Dong C, Loy CC, Tang X (2016) Accelerating the super-resolution convolutional neural network. European conference on computer vision. Springer, Berlin, pp 391–407Google Scholar
  30. 30.
    Dong C, Chen CL, He K et al (2016) Image super-resolution using deep convolutional networks. IEEE Trans Pattern Anal Mach Intell 38(2):295CrossRefGoogle Scholar
  31. 31.
    Krizhevsky A, Sutskever I, Hinton GE (2012) ImageNet classification with deep convolutional neural networks. In: Advances in neural information processing systems, pp 1097–1105Google Scholar
  32. 32.
    Ding L et al (2017) Mixed-noise removal in images based on a convolutional neural network. Pacific-RIM symposium on image and video technology. Springer, Cham, pp 453–464Google Scholar
  33. 33.
    Cao L, Wang C, Li J (2016) Vehicle detection from highway satellite images via transfer learning. Inf Sci 366:177–187MathSciNetCrossRefGoogle Scholar
  34. 34.
    Liu J, Tai XC, Huang H et al (2013) A weighted dictionary learning model for denoising images corrupted by mixed noise. IEEE Trans Image Process 22(3):1108–1120MathSciNetCrossRefzbMATHGoogle Scholar
  35. 35.
    Zhang K et al (2016) Joint learning of multiple regressors for single image super-resolution. IEEE Signal Process Lett 23(1):102–106CrossRefGoogle Scholar

Copyright information

© The Natural Computing Applications Forum 2018

Authors and Affiliations

  • Ling Ding
    • 1
    • 2
  • Huyin Zhang
    • 1
    Email author
  • Jinsheng Xiao
    • 3
  • Bijun Li
    • 4
  • Shejie Lu
    • 2
  • Mohammad Norouzifard
    • 5
  1. 1.School of ComputerWuhan UniversityWuhanChina
  2. 2.College of Computer Science and TechnologyHubei University of Science and TechnologyXianningChina
  3. 3.School of Electronic InformationWuhan UniversityWuhanChina
  4. 4.State Key Laboratory of Information Engineering in Surveying, Mapping and Remote SensingWuhan UniversityWuhanChina
  5. 5.School of Engineering, Computer and Mathematical Sciences, EEE DepartmentAuckland University of TechnologyAucklandNew Zealand

Personalised recommendations