Abstract
Image denoising faces significant challenges, arising from the sources of noise. Specifically, Gaussian, impulse, speckle noises, salt and pepper noise are complicated sources of noise in imaging. Convolutional neural network (CNN) has increasingly received attention in image denoising task. Due to the fast inference and good performance, discriminative learning methods have been widely studied in image denoising. However, these methods mostly learn a specific model for each noise level and require multiple models for denoising images with different noise levels. They also lack flexibility to deal with spatially variant noise, limiting their applications in practical denoising. To address these issues, we propose a deep iterative down-up CNN for image denoising, which alternates between lowering and raising the determination of the feature maps. The proposed network performed on down-sampled sub-images, achieving a good trade-off between inference speed and denoising performance. In contrast to the existing denoisers, the proposed network has several desirable properties, including (i) the ability to handle a wide range of noise levels (i.e., [0, 75]) effectively with a single network and (ii) the ability to remove spatially variant noise by specifying a non-uniform noise level map. In addition, train a network model for five different types of noises, and achieve better performance. Extensive experiments on synthetic and real noisy images are conducted to evaluate the proposed model in comparison with state-of-the-art denoisers. The results show that the proposed model is effective and efficient, making it highly attractive for practical denoising applications.
Similar content being viewed by others
Data availability
The datasets generated and/or analyzed during the current study are available in Berkeley Segmentation Dataset 68, https://arxiv.org/ftp/arxiv/papers/2102/2102.09351.pd.
References
C. Tian, L. Fei, W. Zheng, Y. Xu, W. Zuo, C.W. Lin, Deep learning on image denoising: an overview. Neural Netw. 251–275 (2020). https://doi.org/10.48550/arXiv.1912.13171
J. Cui, K. Gong, N. Guo, C. Wu, X. Meng, K. Kim, K. Zheng, Z. Wu, L. Fu, B. Xu, Z. Zhu, PET image denoising using unsupervised deep learning. Europ. J. Nucl. Med. Mol. Imaging 46, 2780–2789 (2019). https://doi.org/10.1007/s00259-019-04468-4
S. Chaudhary, S. Moon, H. Lu, Fast, efficient, and accurate neuro-imaging denoising via supervised deep learning. Nature Commun. 13, 1–16 (2022). https://doi.org/10.1038/s41467-022-32886-w
D. Liu, B. Wen, J. Jiao, X. Liu, Z. Wang, T.S. Huang, Connecting image denoising and high-level vision tasks via deep learning. IEEE Trans. Image Process. 29, 3695–3706 (2020). https://doi.org/10.1109/TIP.2020.2964518
M. El Helou, S. Süsstrunk, Blind universal Bayesian image denoising with Gaussian noise level learning. IEEE Trans. Image Process. 29, 4885–4897 (2020). https://doi.org/10.1109/TIP.2020.2976814
F. Hashimoto, H. Ohba, K. Ote, A. Teramoto, H. Tsukada, Dynamic PET image denoising using deep convolutional neural networks without prior training datasets. IEEE Access 7, 96594–96603 (2019). https://doi.org/10.1109/ACCESS.2019.2929230
L. Fan, F. Zhang, H. Fan, C. Zhang, Brief review of image denoising techniques. Vis. Comput. Indust. Biomed. Art. 2, 1–12 (2019)
Y. Hou, J. Xu, M. Liu, G. Liu, L. Liu, F. Zhu, L. Shao, NLH: a blind pixel- level non-local method for real-world image denoising. IEEE Trans. Image Process. 2, 5121–5135 (2020)
J. Xu, H. Li, Z. Liang, D. Zhang, L. Zhang, Real-world noisy image denoising: A new benchmark. (2018). https://doi.org/10.48550/arXiv.1804.02603
C. Chen, Z. Xiong, X. Tian, Z.J. Zha, F. Wu, Real-world image denoising with deep boosting. IEEE Trans. Patt. Anal. Mach. Intell. 42(12), 3071–3087 (2019). https://doi.org/10.1109/TPAMI.2019.2921548
R. Ma, H. Hu, S. Xing, Z. Li, Efficient and fast real-world noisy image denoising by combining pyramid neural network and two-pathway unscented Kalman filter. Trans. Image Process. 29, 3927–3940 (2020). https://doi.org/10.1109/TIP.2020.2965294
Y. Song, Y. Zhu, X. Du, Grouped multi-scale network for real-world image denoising. IEEE Signal Process. Lett. 29, 2124–2128 (2020). https://doi.org/10.1109/TIP.2020.2965294
J. Xu, L. Zhang, D. Zhang, External prior guided internal prior learning for real-world noisy image denoising. IEEE Trans. Image Process. 27(6), 2996–3010 (2018). https://doi.org/10.1109/TIP.2018.2811546
X. Li, C. Fan, C. Zhao, L. Zou, S. Tian, NIRN: Self-supervised noisy image reconstruction network for real-world image denoising. Appl. Intell. (2022). https://doi.org/10.1007/s10489-022-03333-6
X. Yu, Z. Fu, C. Ge, A multi-scale generative adversarial network for real- world image denoising. Signal Image Video Process. 16(1), 257–264 (2021). https://doi.org/10.1007/s11760-021-01984-5
X. Wu, M. Liu, Y. Cao, D. Ren, W. Zuo, Unpaired learning of deep image denoising. in European conference on computer vision (Springer, Cham, 2020), pp. 352–368. https://doi.org/10.48550/arXiv.2008.13711
S.G. Bahnemiri, M. Ponomarenko, K. Egiazarian, Learning-based noise Component Map estimation for image denoising. IEEE Signal Process. Lett. 1407–1411 (2020). https://doi.org/10.48550/arXiv.2109.11877
S. Gai, Z. Bao, New image denoising algorithm via improved deep convolutional neural network with perceptive loss. Expert Syst. Appl. 138, 112815 (2019). https://doi.org/10.1016/j.eswa.2019.07.032
C.Z. Wu, X. Chen, D. Ji, S. Zhan, Methods for image denoising using convolutional neural network: a review. Compl. Intell. Syst. 7, 2179–2198 (2019). https://doi.org/10.1007/s40747-021-00428-4
X. Li, J. Xiao, Y. Zhou, Y. Ye, N. Lv, X. Wang, S. Wang, S. Gao, Detail retaining convolutional neural network for image denoising. J. Vis. Commun. Image R 71, 102774 (2020). https://doi.org/10.1016/j.jvcir.2020.102774
H. Yin, Y. Gong, G. Qiu, Fast and efficient implementation of image filtering using a side window convolutional neural network. Signal Process 176, 107717 (2020). https://doi.org/10.1016/j.sigpro.2020.107717
K. Zhang, W. Zou, Y. Chen, D. Meng, L. Zhang, Beyond a Gaussian denoiser: residual learning of deep CNN for image denoising. IEEE Trans. Image Process 26(7), 3142–3155 (2017). https://doi.org/10.1109/TIP.2017.2662206
Xu. Kang, Weixin Li, Xia Wang, Hu. Xiaoyan, Ke. Yan, Xiaojie Wang, Xuan Dong, CUR transformer: a convolutional unbiased regional transformer for image denoising. ACM Trans. Multim. Comput. Commun. Appl. 19(3), 1–22 (2023). https://doi.org/10.1145/3566125
Montrésor S, Picart P, Karray M. The iterative 2D windowed fourier transform: A SOS approach to speckle noise reduction in digital holography. In2017 25th European signal processing conference (EUSIPCO) 2017 Aug 28 (pp. 1544–1548). IEEE.
Y.P. Luo, T. Hwang, Erratum, New arbitrated quantum signature of classical messages against collective amplitude damping noise. Opt. Commun. 15(303), 73 (2013)
G. Ghiasi, T.Y. Lin, Q.V. Le, Dropblock: A regularization method for convolutional networks. Adv. Neural Info. Process. Syst. pp. 10750–10760 (2018). https://doi.org/10.48550/arXiv.1810.12890
S. Gupta, R. Girshick, P. Arbeláez, J. Malik, Learning rich features from RGB-D images for object detection and segmentation. in European conference on computer vision (Springer, Cham, 2014), pp. 345–360. https://doi.org/10.48550/arXiv.1407.5736
J. Li, V. Lavrukhin, B. Ginsburg, R. Leary, O. Kuchaiev, J.M. Cohen, H. Nguyen, R.T. Gadde, Jasper: An end-to-end convolutional neural acoustic model. pp. 71 (2019). https://doi.org/10.48550/arXiv.1904.03288
R.O. Ogundokun, R. Maskeliunas, S. Misra, R. Damaševičius, Improved CNN based on batch normalization and adam optimizer, in Computational science and its applications–ICCSA 2022 workshops: Malaga, Spain, July 4–7, 2022, proceedings, Part V. ed. by O. Gervasi, B. Murgante, S. Misra, M.A. Ana, C. Rocha, C. Garau (Springer International Publishing, Cham, 2022), pp.593–604. https://doi.org/10.1007/978-3-031-10548-7_43
Thakkar, V., Tewary, S. and Chakraborty, C., 2018, January. Batch normalization in convolutional neural networks—A comparative study with CIFAR-10 data. In 2018 fifth international conference on emerging applications of information technology (EAIT) IEEE. (pp. 1–5). doi https://doi.org/10.1109/EAIT.2018.8470438
Acknowledgements
The authors would like to acknowledge the Global Academy of Technology and Kalpataru Institute of Technology for providing facility to do this research work.
Author information
Authors and Affiliations
Contributions
Sundaresha M P and Anandthirtha B. Gudi conceived the idea and supervised the findings of this work. Nandeesh G S assisted with the language of the manuscript. All authors discussed the results and approved final manuscript.
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no competing interest.
Ethical approval
This article does not contain any studies with human participants or animals performed by any of the authors.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Sundaresha, M.P., Anandthirtha, B.G. & Nandeesh, G.S. Color image restoration using DSS-NL-mapping-based multi-noiseNet CNN model. J Opt (2023). https://doi.org/10.1007/s12596-023-01375-8
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s12596-023-01375-8