Abstract
The paper proposed a comparative study for various image restoration techniques using deep learning models. While we capture an image, there is very high chances that the image might get disturb due to some reasons like shaking of hand makes the image blurry and light intensity makes the image very bright or very dark, the device used to capture the image is not up to the mark to take clear and perfect picture, etc. So, due to these reasons, the quality of image goes degraded, unsatisfactory, and not able to take that moment with accuracy. This problem of capturing or accepting noisy images leads to an increasing requirement for a quick solution. So, to overcome with all these problems and get the perfect and clear image, image restoration is the solution. The paper provides detailed insight regarding restoration techniques, majorly focusing on convolution neural network (CNN). At the end, the paper provides an analysis based on some deep learning techniques to get an optimal choice for restoration of image.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
G.X. Zhou, Restoration for motion blurred images of moving objects, in Advanced Engineering Forum 2012, vol. 6. (Trans Tech Publications Ltd.), pp. 1108–1111
M. Maru, M.C. Parikh, Image restoration techniques: a survey. Int. J. Comput. Appl. 160(6), 15–19 (2017)
R.L. Lagendijk, J. Biemond, Basic methods for image restoration and identification, in The essential guide to image processing 2009 Jan 1 (Academic Press), pp. 323–348
C.R. Steffens, L.R. Messias, P.J. Drews-Jr, S.S. Botelho, CNN based image restoration. J. Intell. Rob. Syst. 11, 1–9 (2020)
O.H. Mohammed, B.S. Mahmood, Advance in image and audio restoration and their assessments: a review
K. Zhang, W. Zuo, S. Gu, L. Zhang, Learning deep CNN denoiser prior for image restoration, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2017), pp. 3929–3938
Z. Jin, M.Z. Iqbal, D. Bobkov, W. Zou, X. Li, E. Steinbach, A flexible deep CNN framework for image restoration. IEEE Trans. Multimedia 22(4), 1055–1068 (2019)
Y. Zhang, Y. Tian, Y. Kong, B. Zhong, Y. Fu, Residual dense network for image restoration. IEEE Trans. Pattern Anal. Mach. Intell. 43(7), 2480–2495 (2020)
A.K. Boyat, B.K. Joshi, A review paper: noise models in digital image processing. arXiv preprint arXiv:1505.03489. 2015 May 13
M.D. Sontakke, M.S. Kulkarni, Different types of noises in images and noise removing technique. Int. J. Adv. Technol. Eng. Sci. 3(1), 102–115 (2015)
I. Bashir, A. Majeed, O. Khursheed, Image restoration and the various restoration techniques used in the field of digital image processing. Int. J. Comput. Sci. Mob. Comput. 6(6), 390–393 (2017)
C. Dong, Y. Deng, C.C. Loy, X. Tang, Compression artifacts reduction by a deep convolutional network, in Proceedings of the IEEE International Conference on Computer Vision (2015), pp. 576–584
K. Zhang, W. Zuo, 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)
Y. Tai, J. Yang, X. Liu, C. Xu, Memnet: a persistent memory network for image restoration, in Proceedings of the IEEE International Conference on Computer Vision (2017), pp. 4539–4547
P. Liu, H. Zhang, K. Zhang, L. Lin, W. Zuo, Multi-level wavelet-CNN for image restoration, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops (2018), pp. 773–782
K. Uchida, M. Tanaka, M. Okutomi, Non-blind image restoration based on convolutional neural network, in 2018 IEEE 7th Global Conference on Consumer Electronics (GCCE) (IEEE, 2018), pp. 40–44
https://www.probabilitycourse.com/chapter9/9_1_2_MAP_estimation.php
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Sharma, D., Sharma, S., Patil, H. (2022). CNN-Based Optimal Image Restoration and Comparative Approaches. In: Pundir, A.K.S., Yadav, N., Sharma, H., Das, S. (eds) Recent Trends in Communication and Intelligent Systems. Algorithms for Intelligent Systems. Springer, Singapore. https://doi.org/10.1007/978-981-19-1324-2_19
Download citation
DOI: https://doi.org/10.1007/978-981-19-1324-2_19
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-19-1323-5
Online ISBN: 978-981-19-1324-2
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)