Skip to main content
SpringerLink
Log in

Densely connected network for impulse noise removal

  • Theoretical advances
  • Published:
Pattern Analysis and Applications Aims and scope Submit manuscript

Abstract

Recently, a new convolutional neural network (CNN) architecture, dubbed as densely connected convolutional network (DenseNet), has shown excellent results on image classification tasks. The idea of DenseNet is based on the observation that if each layer is directly connected to every other layer in a feed-forward fashion, then the network will be more accurate and easier to train. In this study, we extend DenseNet to deal with the problem of impulse noise reduction. It aims to explore the densely connected network for impulse noise removal (DNINR), which utilizes CNN to learn pixel-distribution features from noisy images. Compared with the traditional median filter-based and variational regularization methods that utilize the spatial neighbor information around the pixels and optimize in an iterative manner, it is more efficient to capture multi-scale contextual information and directly tackles the original image. Additionally, DNINR turns to capture the pixel-level distribution information by means of wide and transformed network learning. In terms of edge preservation and noise suppression, the proposed DNINR consistently achieved significantly superior performance, which is better than current state-of-the-art methods, particularly at extremely high noise levels.

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

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14

Similar content being viewed by others

References

  1. Abreu E, Lightstone M, Mitra SK, Arakawa K (1996) A new efficient approach for the removal of impulse noise from highly corrupted images. IEEE Trans Image Process 5:1012–1025

    Google Scholar 

  2. Nodes T, Gallagher N (1982) Median filters: some modifications and their properties. IEEE Trans Acoust Speech Signal Process 30(5):739–746

    Google Scholar 

  3. Singh KM, Bora PK, Singh SB (2002) Rank-ordered mean filter for removal of impulse noise from images. In: Proceedings of IEEE conference industrial technology

  4. Hwang H, Haddad RA (1995) Adaptive median filters: new algorithms and results. IEEE Trans Image Process 4(4):499–502

    Google Scholar 

  5. Wang Z, Zhang D (1999) Progressive switching median filter for the removal of impulse noise from highly corrupted images. IEEE Circuits Syst Soc 46(1):78–80

    Google Scholar 

  6. Nikolova M (2004) A variational approach to remove outliers and impulse noise. J Math Imaging Vis 20(1):99–120

    MathSciNet  MATH  Google Scholar 

  7. Rodriguez P, Wohlberg B (2009) A generalized vector-valued total variation algorithm. In: Proceedings of IEEE international conference on image processing, pp 1309–1312

  8. Wright J, Ma Y, Mairal J, Sapiro G, Huang T, Yan S (2010) Sparse representation for computer vision and pattern recognition. Proc IEEE 98(6):1031–1044

    Google Scholar 

  9. Wang S, Liu Q, Xia Y, Dong P, Luo J, Feng D (2013) Dictionary learning based impulse noise removal via L1–L1 minimization. Signal Process 93(9):2696–2708

    Google Scholar 

  10. Chen C, Liu L, Chen L, Tang Y, Zhou T (2015) Weighted couple sparse representation with classified regularization for impulse noise removal. IEEE Trans Image Process 24(11):4014–4026

    MathSciNet  MATH  Google Scholar 

  11. Saikrishna P, Bora PK (2013) Detection and removal of random-valued impulse noise from images using sparse representations. In: Proceedings of IEEE international conference on image processing, pp 1197–1201

  12. Ma L, Yu J, Zeng T (2013) Sparse representation prior and total variation-based image deblurring under impulse noise. SIAM J Imaging Sci 6(4):2258–2284

    MathSciNet  MATH  Google Scholar 

  13. Zhou Y, Lin M, Xu S, Zang H, He H, Li Q, Guo J (2016) An image denoising algorithm for mixed noise combining nonlocal means filter and sparse representation technique. J Vis Commun Image Represent 41:74–86

    Google Scholar 

  14. Chen L, Liu L, Chen CP (2016) A robust bi-sparsity model with non-local regularization for mixed noise reduction. Inf Sci 354:101–111

    Google Scholar 

  15. Huang T, Dong W, Xie X, Shi G, Bai X (2017) Mixed noise removal via Laplacian scale mixture modeling and nonlocal low-rank approximation. IEEE Trans Image Process 26(7):3171–3186

    MathSciNet  MATH  Google Scholar 

  16. Wang N, Tao D, Gao X, Li X, Li J (2014) A comprehensive survey to face hallucination. Int J Comput Vis 106(1):9–30

    Google Scholar 

  17. Wang N, Gao X, Sun L, Li J (2017) Bayesian face sketch synthesis. IEEE Trans Image Process 26(3):1264–1274

    MathSciNet  MATH  Google Scholar 

  18. Wang N, Gao X, Li J (2018) Random sampling for fast face sketch synthesis. Pattern Recogn 76:215–227

    Google Scholar 

  19. Wang N, Gao X, Sun L, Li J (2018) Anchored neighborhood index for face sketch synthesis. IEEE Trans Circuits Syst Video Technol 28(9):2154–2163

    Google Scholar 

  20. Jain V, Seung HS (2008) Natural image denoising with convolutional networks. In: Proceedings of NIPS, pp 769–776

  21. Vincent P, Larochelle H, Bengio Y, Manzagol P (2008) Extracting and composing robust features with denoising autoencoders. In: Proceedings of international conference on machine learning, pp 1096–1103

  22. Xie J, Xu L, Chen E (2012) Image denoising and inpainting with deep neural networks. Proc NIPS 26:1–8

    Google Scholar 

  23. He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of IEEE conference on CVPR, pp 770–778

  24. Mao X, Shen C, Yang Y (2016) Image restoration using very deep convolutional encoder-decoder networks with symmetric skip connections. In: Proceedings of NIPS, pp 2802–2810

  25. 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):3142–3155

    MathSciNet  MATH  Google Scholar 

  26. Huang G, Liu Z, Maaten LVD, Weinberger KQ (2017) Densely connected convolutional networks. In: Proceedings of IEEE conference on CVPR, pp 4700–4708

  27. Nair V, Hinton GE (2010) Rectified linear units improve restricted Boltzmann machines. In: Proceedings of IEEE conference on ICML, pp 807–814

  28. Martin D, Fowlkes C, Tal D, Malik J (2001) A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics. Proc IEEE Conf ICCV 2:416–423

    Google Scholar 

  29. Lim B, Son S, Kim H, Nah S, Lee K (2017) Enhanced deep residual networks for single image super-resolution. In: Proceedings of IEEE conference on CVPR workshops

  30. Kim J, Kwon Lee J, Mu Lee K (2016) Accurate image super-resolution using very deep convolutional networks. In: Proceedings of IEEE conference on CVPR, pp 1646–1654

  31. Rodríguez P, Wohlberg B (2008) Efficient minimization method for a generalized total variation functional. IEEE Trans Image Process 18(2):322–332

    MathSciNet  MATH  Google Scholar 

  32. Zhang M, Liu Y, Li G, Qin B, Liu Q (2020) Iterative scheme-inspired network for impulse noise removal. Pattern Anal Appl 23(1):135–145

    MathSciNet  Google Scholar 

  33. Wang Z, Bovik AC, Sheikh HR, Simoncelli EP (2004) Image quality assessment: from error visibility to structural similarity. IEEE Trans Image Process 13(4):600–612

    Google Scholar 

Download references

Acknowledgements

This work was partly supported by the National Natural Science Founding of China (NSFC) (61871206, 61362009, 61661031), the Natural Science Foundation of Jiangxi Province (20181BAB202003), the Key Scientist Plan of Jiangxi Province (20171BBH80023, GJJ170566) and Fund for postgraduate of Nanchang University (CX2018144).

Author information

Authors and Affiliations

  1. Department of Electronic Information Engineering, Nanchang University, Nanchang, 330031, China

    Guanyu Li, Xiaoling Xu, Minghui Zhang & Qiegen Liu

Authors
  1. Guanyu Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Xiaoling Xu
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Minghui Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Qiegen Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Qiegen Liu.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Li, G., Xu, X., Zhang, M. et al. Densely connected network for impulse noise removal. Pattern Anal Applic 23, 1263–1275 (2020). https://doi.org/10.1007/s10044-020-00871-y

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10044-020-00871-y

Keywords

Search

Navigation