Advertisement

Multimedia Tools and Applications

, Volume 78, Issue 14, pp 19945–19960 | Cite as

Multi-scale dilated convolution of convolutional neural network for image denoising

  • Yanjie Wang
  • Guodong WangEmail author
  • Chenglizhao Chen
  • Zhenkuan Pan
Article
  • 181 Downloads

Abstract

Convolutional Neural Network has achieved great success in image denoising. The conventional methods usually sense those beyond scope contextual info at the expense of the receptive filed shrinking, which easily lead to multiple limitations. In this paper, we have proposed a concise and efficient convolutional neural network naming Multi-scale Dilated Convolution of Convolutional Neural Network (MsDC), which attempt to utilize the newly designed multi-scale dilated convolution strategy to handle the above mentioned obstinate limitation. The proposed multi-scale dilated convolution module uses the dilated filters to systematically aggregate multi-scale contextual information without reducing the receptive field. The behind rationale of our method is based on the phenomenon that the dilated convolution can effectively expand the corresponding receptive field while conserving those valuable contextual information. Meanwhile, we also utilize residual learning method to learn the residuals directly to speed up the learning procedur. Compared to the state-of-the-art methods, the results have suggested that our method can remove image noise more effectively and efficiently. Our MsDC code can be download at https://github.com/doctorwgd/MsDC.

Keywords

Image processing Image denoising Deep learning Dilated convolution 

Notes

Acknowledgements

This work was supported by the National Natural Science Foundation of China (No. 61772294) and the National “Twelfth Five-Year” development plan of science and technology (No.2014BAG03B05).

References

  1. 1.
    Aharon M, Elad M, Bruckstein A (2006) K-SVD: An Algorithm for Designing Over complete Dictionaries for Sparse Representation. IEEE Transactions, Signal Processing 54(11):4311–4322zbMATHGoogle Scholar
  2. 2.
    Cao L, Huang W, Sun F (2016) Building feature space of extreme learning machine with sparse denoising stacked-autoencoder. Neurocomputing 174:60–71Google Scholar
  3. 3.
    Chen C, Li S, Qin H, Pan Z, Yang G (2018) Bi-level Feature Learning for Video Saliency Detection. IEEE Transactions on Multimedia 20(12):3324–3336Google Scholar
  4. 4.
    Chen C, Li S, Wang Y, Qin H, Hao A (2017) Video saliency detection via spatial-temporal fusion and low-rank coherency diffusion. IEEE Trans Image Process 26(7):3156–3170MathSciNetzbMATHGoogle Scholar
  5. 5.
    Chen L, Papandreou G, Kokkinos I, Murphy K, Yuille AL (2018) DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs. IEEE Trans Pattern Anal Mach Intell 40(4):834–848Google Scholar
  6. 6.
    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):1256–1272Google Scholar
  7. 7.
    Dabov K, Foi A, Katkovnik V, Egiazarian K (2007) Image Denoising by Sparse 3-D Transform-Domain Collaborative Filtering. IEEE Transactions on Image Process 16(8):2080–2095MathSciNetGoogle Scholar
  8. 8.
    Diwakar M, Kumar M (2018) A review on CT image noise and its denoising. Biomedical Signal Processing and Control 42:73–88Google Scholar
  9. 9.
    Dong W, Shi G, Li X (2013) Nonlocal image restoration with bilateral variance estimation: a low-rank approach, IEEE Transactions on Image Processing A Publication of the IEEE Signal Processing. Society 22(2):700–711Google Scholar
  10. 10.
    Dong W, Zhang L, Shi G, Li X (2013) Nonlocally centralized sparse representation for image restoration. IEEE Trans Image Process 22(4):1620–1630MathSciNetzbMATHGoogle Scholar
  11. 11.
    Duchi J, Hazan E, Singer Y (2011) Adaptive subgradient methods for online learning and stochastic optimization. J Mach Learn Res 12:2121–2159MathSciNetzbMATHGoogle Scholar
  12. 12.
    Gu S, Zhang L, Zuo W et al (2014) Weighted Nuclear Norm Minimization with Application to Image Denoising, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2862–2869Google Scholar
  13. 13.
    He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition, IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778Google Scholar
  14. 14.
    Huang Z, Li Z, Huang H, Li Z, Hou L (2016) Comparison of different image denoising algorithms for Chinese calligraphy images. Neurocomputing 188:102–112Google Scholar
  15. 15.
    Ioffe S, Szegedy C (2015) Batch normalization: Accelerating deep network training by reducing internal covariate shift. International Conference on Machine Learning, pp. 448–456Google Scholar
  16. 16.
    Jain V, Seung S (2008) Natural image denoising with convolutional networks, International Conference on Neural Information Processing Systems, Curran Associates Inc. 769–776Google Scholar
  17. 17.
    Jian J, Shuang-Xing X, Xiao L (2014) An Adaptive Thresholding Image Denoising Method Based on Morphological Component Analysis and Contourlet Transform. Pattern Recognition & Artificial Intelligence 27(6):561–568Google Scholar
  18. 18.
    Kim Y, Jung H, Min D et al (2017) Deeply Aggregated Alternating Minimization for Image Restoration, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 284–292Google Scholar
  19. 19.
    Krizhevsky A, Sutskever I, Hinton G (2012) ImageNet classification with deep convolutional neural networks, International Conference on Neural Information Processing Systems, Curran Associates Inc, 1097–1105Google Scholar
  20. 20.
    Putzky P, Welling M (2017) Recurrent Inference Machines for Solving Inverse Problems, arXiv preprint arXiv: 1706.04008Google Scholar
  21. 21.
    Roth S, Black M (2009) Fields of Experts. Int J Comput Vis 82(2):205–229Google Scholar
  22. 22.
    Simonyan K, Zisserman A (2015) Very Deep Convolutional Networks for Large-Scale Image Recognition. International Conference for Learning RepresentationsGoogle Scholar
  23. 23.
    Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A (2015) Going deeper with convolutions. IEEE Conference on Computer Vision and Pattern Recognition, pp. 1–9Google Scholar
  24. 24.
    Wang X, Liu X, Zhang A et al (2016) Undecimated Wavelet Bayesian Image Denoising Method with Its Threshold Determined by Curve Fitting. Pattern Recognition and Artificial Intelligence 29(4):322–331Google Scholar
  25. 25.
    Xie J, Xu L, Chen E (2012) Image denoising and in painting with deep neural networks, International Conference on Neural Information Processing Systems, Curran Associates Inc., pp. 341–349Google Scholar
  26. 26.
    Xu J, Zhang L, Zhang D, et al (2017) Multi-channel Weighted Nuclear Norm Minimization for Real Color Image Denoising, IEEE International Conference on Computer Vision (ICCV), Venice, pp. 1105–1113Google Scholar
  27. 27.
    Yu F, Koltun V (2016) Multi-scale context aggregation by dilated convolutions, International Conference on Learning Representations (ICLR)Google Scholar
  28. 28.
    Zeng N, Zhang H, Li Y, Liang J, Dobaie AM (2017) Denoising and deblurring gold immunochromatographic strip images via gradient projection algorithms. Neurocomputing 247:165–172Google Scholar
  29. 29.
    Zhang K, Zuo W, Chen Y, Meng D, Zhang L (2017) Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising. IEEE Trans Image Process 26(7):3142–3155MathSciNetzbMATHGoogle Scholar
  30. 30.
    Zoran D, Weiss Y (2011) From learning models of natural image patches to whole image restoration. International Conference on Computer Vision:479–486Google Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2019

Authors and Affiliations

  • Yanjie Wang
    • 1
  • Guodong Wang
    • 1
    Email author
  • Chenglizhao Chen
    • 1
  • Zhenkuan Pan
    • 1
  1. 1.College of Computer Science and TechnologyQingdao UniversityQingdaoPeople’s Republic of China

Personalised recommendations