A Comprehensive Review of Image Restoration and Noise Reduction Techniques
Article Sidebar
Main Article Content
Abstract
Images play a crucial role in modern life and find applications in diverse fields, ranging from preserving memories to conducting scientific research. However, images often suffer from various forms of degradation such as blur, noise, and contrast loss. These degradations make images difficult to interpret, reduce their visual quality, and limit their practical applications.
To overcome these challenges, image restoration and noise reduction techniques have been developed to recover degraded images and enhance their quality. These techniques have gained significant importance in recent years, especially with the increasing use of digital imaging in various fields such as medical imaging, surveillance, satellite imaging, and many others.
This paper presents a comprehensive review of image restoration and noise reduction techniques, encompassing spatial and frequency domain methods, and deep learning-based techniques. The paper also discusses the evaluation metrics utilized to assess the effectiveness of these techniques and explores future research directions in this field. The primary objective of this paper is to offer a comprehensive understanding of the concepts and methods involved in image restoration and noise reduction.
Article Details
References
Agrawal, Rashmi. "Analyzing the Performance of Image Denoising Techniques." Bangladesh Journal of Bioethics 13.3 (2022): 8-14.
Agustsson, E., & Timofte, R. (2017). NTIRE 2017 challenge on single image super-resolution: Dataset and study. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) (pp. 1110-1121). IEEE.
Anis, A., & Breuss, M. (2018). A review on deep learning in medical image reconstruction. Medical Physics, 45(9), e735-e762.
Buades, A., Coll, B., & Morel, J. M. (2005). A non-local algorithm for image denoising. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR) (Vol. 2, pp. 60-65). IEEE.
Chen, D., Yuan, J., Liao, J., & Wang, N. (2016). Similarity prior based simultaneous image segmentation and bias field estimation. IEEE Transactions on Image Processing, 25(6), 2772-2785.
Chen, J., Tan, P., Li, Q., Liu, X., & Shen, Z. (2018). Learning to see in the dark. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 3291-3300).
Chen, Q., & Pock, T. (2016). Trainable nonlinear reaction diffusion: A flexible framework for fast and effective image restoration. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(6), 1256-1272.
Chen, T., Zhu, L., Li, S., Liu, Y., Chen, J., & Huang, X. (2021). High-frequency pattern enhancement for image restoration. IEEE Transactions on Image Processing, 30, 2628-2642. (High-frequency pattern enhancement)
Chen, Y., Tai, X. C., & Liu, C. (2015). Image smoothing via l0 gradient minimization. ACM Transactions on Graphics (TOG), 34(1), 12.
Dabov, K., Foi, A., Katkovnik, V., & Egiazarian, K. (2007). Image denoising by sparse 3D transform-domain collaborative filtering. IEEE Transactions on Image Processing, 16(8), 2080-2095.
Dhanapal, R., & Nair, M. S. (2020). Image restoration of historical artworks using deep learning techniques. In International Conference on Machine Learning and Data Engineering (pp. 333-343). Springer, Cham.
Dong, C., Loy, C. C., He, K., & Tang, X. (2016). Image super-resolution using deep convolutional networks
Fu, X., Zhang, Y., Huang, H., & Gao, Y. (2020). Learning joint spatial-temporal transforms for video denoising. IEEE Transactions on Image Processing, 29, 6496-6511.
Gao, J., Zhang, W., Wang, Y., & Shi, Z. (2021). Image restoration of degraded forensic footprints via convolutional neural network. IEEE Access, 9, 146399-146412.
Gharbi, M., Paris, S., & Durand, F. (2016). Deep joint demosaicking and denoising. ACM Transactions on Graphics (TOG), 35(6), 191.
He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 770-778). IEEE.
Heena, Ayesha, et al. "Machine learning based biomedical image processing for echocardiographic images." Multimedia Tools and Applications (2022): 1-16.
Huang, G., Liu, Z., van der Maaten, L., & Weinberger, K. Q. (2017). Densely connected convolutional networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 4700-4708). IEEE.
Huang, J., Li, Y., Yang, J., & Tao, D. (2014). Learning recursive filters for low-level vision via a hybrid neural network. IEEE Transactions on Neural Networks and Learning Systems, 26(12), 3160-3173.
Kheradmand, A., Afshari, H., & Aghagolzadeh, A. (2019). Medical image restoration and enhancement using convolutional neural networks. Biocybernetics and Biomedical Engineering, 39(2), 545-553.
Kim, J., Kwon Lee, J., & Mu Lee, K. (2016). Deeply-recursive convolutional network for image super-resolution. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 1637-1645). IEEE.
Kim, J., Lee, J. K., & Lee, K. M. (2016). Accurate image super-resolution using very deep convolutional networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 1646-1654). IEEE.
Krishnan, D., & Fergus, R. (2009). Fast image deconvolution using hyper-Laplacian priors. Advances in Neural Information Processing Systems (NIPS), 22, 1033-1041.
Lefkimmiatis, S. (2018). Universal denoising networks: A novel CNN architecture for image denoising. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 3204-3213). (Universal denoising network)
Lefkimmiatis, S., & Unser, M. (2017). Nonlocal means of gradients for image restoration. IEEE Transactions on Image Processing, 26(9), 4389-4402.
Li, Y., Qi, H., Dai, J., Ji, X., & Wei, Y. (2019). Deep progressive reinforcement learning for skeleton-based action recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 5323-5332). (Progressive learning)
Li, Y., Wang, R., & Wang, C. (2020). A deep learning approach to image colorization and restoration of faded old photos. Multimedia Tools and Applications, 79(13-14), 9515-9534.
Liu, G., Lin, Z., Yan, S., Sun, J., Yu, Y., & Ma, Y. (2013). Robust recovery of subspace structures by low-rank representation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 35(1), 171-184.
Liu, S., Huang, D., Wang, Y., & Wang, T. (2018). Multi-level wavelet-CNN for image restoration. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 2734-2742). (Multi-level wavelet transform)
Mairal, J., Bach, F., Ponce, J., & Sapiro, G. (2009). Online dictionary learning for sparse coding. In Proceedings of the International Conference on Machine Learning (ICML) (pp. 689-696).
Mao, X., Shen, C., & Yang, Y. B. (2016). Image restoration using very deep convolutional encoder-decoder networks with symmetric skip connections. In Advances in Neural Information Processing Systems (pp. 2802-2810). (Convolutional encoder-decoder network)
Qin, C., Li, Y., Liu, Z., Zhang, Y., Zhang, Y., Wang, S., & Liu, Y. (2021). Multiscale residual network for non-blind image restoration. IEEE Transactions on Circuits and Systems for Video Technology, 31, 1703-1717. (Multiscale residual network)
Ren, W., Liu, X., Zhang, H., Pan, J., & Cao, X. (2019). Low-light image enhancement via a deep hybrid network. IEEE Transactions on Image Processing, 28(11), 5466-5479.
Rudin, L. I., Osher, S., & Fatemi, E. (1992). Nonlinear total variation based noise removal algorithms. Physica D: Nonlinear Phenomena, 60(1-4), 259-268.
Sun, Y., Chen, Y., Liang, K., Wang, X., & Tang, X. (2013). Image super-resolution using gradient profile prior. In Proceedings of the IEEE International Conference on Computer Vision (ICCV) (pp. 1723-1730). IEEE.
Sutskever, I., Martens, J., Dahl, G., & Hinton, G. (2013). On the importance of initialization and momentum in deep learning. In Proceedings of the International Conference on Machine Learning (ICML) (pp. 1139-1147).
Tai, Y., Yang, J., & Liu, X. (2017). Image super-resolution via deep recursive residual network. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 2790-2798). (Recursive residual network)
Tanaka, H., & Okutomi, M. (2019). Image restoration using deep learning: A review. IEICE Transactions on Information and Systems, 102(12), 2179-2193.
Wang, Z., Bovik, A. C., Sheikh, H. R., & Simoncelli, E. P. (2004). Image quality assessment: From error visibility to structural similarity. IEEE Transactions on Image Processing, 13(4), 600-612.
Xiao, Y., Qi, C., & Zhang, J. (2019). Scratch removal in old film images using generative adversarial networks. IEEE Access, 7, 126407-126415.
Xu, M., Zhang, H., Guo, X., Wang, X., & Zhang, Z. (2022). A novel framework for blind image restoration via meta-learning. IEEE Transactions on Image Processing, 31, 598-610. (Meta-learning)
Yuan, L., & Sun, J. (2017). Automatic dust and scratches removal from old film using convolutional neural networks. Journal of Electronic Imaging, 26(2), 023017.
Zeng, G., Guo, J., Zheng, H., Li, S., & Wang, Y. (2020). Learning to denoise dental CT images with weak supervision. IEEE Transactions on Medical Imaging, 39(3), 630-640.
Zhang, K., Zuo, W., & Zhang, L. (2017). FFDNet: Toward a fast and flexible solution for CNN-based image denoising. IEEE Transactions on Image Processing, 27(9), 4608-4622.
Zhang, K., Zuo, W., & Zhang, L. (2018). Learning deep CNN denoiser prior for image restoration. IEEE Transactions on Image Processing, 27(6), 2944-2956.
Zhang, K., Zuo, W., Chen, Y., Meng, D., & Zhang, L. (2018). Beyond a gaussian denoiser: Residual learning of deep CNN for image denoising. IEEE Transactions on Image Processing, 26(7), 3142-3155.
Zhang, Y., Tian, Y., & Kong, Y. (2019). Residual dense network for image restoration. IEEE Transactions on Image Processing, 28(5), 2614-2623.
Zhang, Y., Tian, Y., Kong, Y., Zhong, B., & Fu, Y. (2020). Hybrid residual dense network for image restoration. IEEE Transactions on Image Processing, 29, 4282-4294. (Residual dense network)
Zhou, T., Ye, Y., Zhu, Y., & Zhang, Y. (2020). Deep residual learning for low-dose CT denoising with convolutional neural network. Journal of X-Ray Science and Technology, 28(5), 895-909.
Zhu, H., Zhang, X., & Li, Y. (2020). Single image noise reduction via a deep spatial-channel attention network. IEEE Transactions on Image Processing, 29, 4379-4390.
Zhu, Z., & Milanfar, P. (2010). A signal-dependent Fourier thresholding technique for image denoising. IEEE Transactions on Image Processing, 19(12), 3079-3093.
Zontak, M., & Irani, M. (2011). Internal statistics of a single natural image. In Proceedings of the IEEE International Conference on Computer Vision (ICCV) (pp. 977-984). IEEE.
Venusamy, K. ., Muthuramalingam, M. ., S. Kannadhasan, & R. Vanithamani. (2023). Enhancement of PAPR Abatement for FBMC System. International Journal of Intelligent Systems and Applications in Engineering, 11(1), 239–245. Retrieved from https://ijisae.org/index.php/IJISAE/article/view/2463