Deep learning-based image denoising method
Article Sidebar
Main Article Content
Abstract
Image denoising is crucial in image processing and computer vision. Noise present in digital images captured by cameras, smart phones, and other devices can severely degrade image quality and negatively impact image-based tasks such as object recognition and image segmentation. Image-denoising algorithms aim to remove the noise from the images while preserving their key features. Deep learning-based methods have demonstrated better performance than conventional ones. In light of these developments, a novel image-denoising method was proposed based on a deep neural network that utilizes both residual connections and attention mechanisms. This method was trained on a large dataset of noisy and clean images to learn the mapping between the two. This technique achieved state-of-the-art denoising performance on various benchmarks and exhibited excellent generalization capability to real-world noisy images. In addition, it was computationally efficient and could process high-resolution images in real time.
Downloads
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
References
Buades, A., Coll, B., & Morel, J. M. (2005). A review of image denoising algorithms, with a new one. Multiscale Modeling & Simulation, 4(2), 490–530. https://doi.org/10.1137/040616024
Chaitanya, N. K., & Sreenivasulu, P. (2014a, February 13–14). Removal of salt and pepper noise using advanced modified decision based unsymmetric trimmed median filter [Conference session]. 2014 International Conference on Electronics and Communication Systems (ICECS), Coimbatore, India. https://doi.org/10.1109/ECS.2014.6892524
Chaitanya, N. K., & Sreenivasulu, P. (2014b). Removal of salt and pepper noise for various images using median filters: A comparative study. The IUP Journal of Telecommunications, 6(2), 54–69.
Dabov, K., Foi, A., Katkovnik, V., & Egiazarian, K. (2007). Image denoising by sparse 3-D transform-domain collaborative filtering. IEEE Transactions on Image Processing, 16(8), 2080–2095. https://doi.org/10.1109/TIP.2007.901238
Elad, M., & Aharon, M. (2006). Image denoising via sparse and redundant representations over learned dictionaries. IEEE Transactions on Image Processing, 15(12), 3736–3745. https://doi.org/10.1109/TIP.2006.881969
Gu, S., Zhang, L., Zuo, W., & Feng, X. (2014). Weighted nuclear norm minimization with application to image denoising. IEEE Xplore, 2014, 2862–2869. https://doi.org/10.1109/CVPR.2014.366
Hashimoto, F., Onishi, Y., Ote, K., Tashima, H., Reader, A. J., & Yamaya, T. (2024). Deep learning-based PET image denoising and reconstruction: A review. Radiological Physics and Technology, 17(1), 24–46. https://doi.org/10.1007/s12194-024-00780-3
He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 770–778). IEEE. https://doi.org/10.1109/CVPR.2016.90
Huang, H., Hu, H., & Yi, C. (2018). Image denoising based on spatial and spectral similarity using 3D-DCNN. Journal of Visual Communication and Image Representation, 56, 221–231.
Jebur, R. S., Zabil, M. H. B. M., Hammood, D. A., & Cheng, L. K. (2024). A comprehensive review of image denoising in deep learning. Multimedia Tools and Applications, 83(20), 58181–58199. https://doi.org/10.1007/s11042-023-17468-2
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017). ImageNet classification with deep convolutional neural networks. Communications of the ACM, 60(6), 84–90. https://doi.org/10.1145/3065386
LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. Nature, 521, 436–444. https://doi.org/10.1038/nature14539
Li, L., Hou, W., Zhang, X., & Ding, M. (2013). Gpu-based block-wise nonlocal means denoising for 3D ultrasound images. Ultrasound, 2013(1), Article 921303. https://doi.org/10.1155/2013/921303
Li, W., Liu, H., & Wang, J. (2021). A deep learning method for denoising based on a fast and flexible convolutional neural network. IEEE Transactions on Geoscience and Remote Sensing, 60, Article 5902813. https://doi.org/10.1109/TGRS.2021.3073001
Liu, P., Zhang, H., Lian, W., & Zuo, W. (2019). Multi-level wavelet convolutional neural networks. IEEE Access, 7, 74973–74985. https://doi.org/10.48550/arXiv.1907.03128
Mahmoudi, M., & Sapiro, G. (2009). Fast image and video denoising via nonlocal means of similar neighborhoods. IEEE Signal Processing Letters, 12(12), 839–842. https://doi.org/10.1109/LSP.2005.859509
Portilla, J., & Simoncelli, E. P. (2000). A parametric texture model based on joint statistics of complex wavelet coefficients. International Journal of Computer Vision, 40(1), 49–70. https://doi.org/10.1023/A:1026553619983
Thakur, R. S., Chatterjee, S., Yadav, R. N., & Gupta, L. (2021). Image de-noising with machine learning: A review. IEEE Access, 9, 93338–93363. https://doi.org/10.1109/ACCESS.2021.3092425
Zhang, K., Zuo, W., Gu, S., & Zhang, L. (2017). Learning deep CNN denoiser prior for image restoration. Computer Vision and Pattern Recognition (CVPR), 3929–3938. https://doi.org/10.48550/arXiv.1704.03264
