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.
Similar content being viewed by others
References
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
Nodes T, Gallagher N (1982) Median filters: some modifications and their properties. IEEE Trans Acoust Speech Signal Process 30(5):739–746
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
Hwang H, Haddad RA (1995) Adaptive median filters: new algorithms and results. IEEE Trans Image Process 4(4):499–502
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
Nikolova M (2004) A variational approach to remove outliers and impulse noise. J Math Imaging Vis 20(1):99–120
Rodriguez P, Wohlberg B (2009) A generalized vector-valued total variation algorithm. In: Proceedings of IEEE international conference on image processing, pp 1309–1312
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
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
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
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
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
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
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
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
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
Wang N, Gao X, Sun L, Li J (2017) Bayesian face sketch synthesis. IEEE Trans Image Process 26(3):1264–1274
Wang N, Gao X, Li J (2018) Random sampling for fast face sketch synthesis. Pattern Recogn 76:215–227
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
Jain V, Seung HS (2008) Natural image denoising with convolutional networks. In: Proceedings of NIPS, pp 769–776
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
Xie J, Xu L, Chen E (2012) Image denoising and inpainting with deep neural networks. Proc NIPS 26:1–8
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
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
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
Huang G, Liu Z, Maaten LVD, Weinberger KQ (2017) Densely connected convolutional networks. In: Proceedings of IEEE conference on CVPR, pp 4700–4708
Nair V, Hinton GE (2010) Rectified linear units improve restricted Boltzmann machines. In: Proceedings of IEEE conference on ICML, pp 807–814
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
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
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
Rodríguez P, Wohlberg B (2008) Efficient minimization method for a generalized total variation functional. IEEE Trans Image Process 18(2):322–332
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
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
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
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
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
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10044-020-00871-y