A Novel U-Net Architecture with Attention Mechanism for Image Denoising
Keywords:
U-Net, attention mechanism, Gaussian filter, image denoising, Convolutional Neural NetworksAbstract
In this study, we present an enhanced U-Net-based model for effective image denoising, incorporating a hybrid attention mechanism that combines both spatial and channel attention. These dual attention blocks enable the network to dynamically focus on relevant features while suppressing noise across both dimensions, thereby improving denoising performance. To further refine the output and enhance perceptual quality, a Gaussian filter is applied as a post-processing step, resulting in smoother edges and better texture continuity. The model also leverages Batch Normalization and Dropout techniques to stabilize training and prevent overfitting. Experimental evaluations were conducted on the CIFAR-10 and DIV2K datasets using standard performance metrics. The proposed model achieved an accuracy of 82%, a loss of 0.01, a PSNR of 37 dB, and an SSIM of 0.94—outperforming several state-of-the-art denoising methods. These results confirm the model’s strong ability to preserve structural and textural image details while significantly reducing noise. The combination of convolutional deep learning, hybrid attention mechanisms, and post-processing filtering offers a powerful and scalable solution for image restoration tasks. Furthermore, it demonstrates strong potential for practical applications in real-world scenarios such as image quality enhancement and medical imaging.
Downloads
References
A. Buades, B. Coll, and J. M. Morel, “A non-local algorithm for image denoising,” in *Proc. CVPR*, 2005, pp. 60–65.
K. Dabov, A. Foi, V. Katkovnik, and K. Egiazarian, “Image denoising by sparse 3D transform-domain collaborative filtering,” *IEEE Trans. Image Process.*, vol. 16, no. 8, pp. 2080–2095, Aug. 2007.
K. Zhang, W. Zuo, and L. Zhang, “Beyond a Gaussian denoiser: Residual learning of deep CNN for image denoising,” *IEEE Trans. Image Process.*, vol. 26, no. 7, pp. 3142–3155, Jul. 2017.
X. Mao, C. Shen, and Y.-B. Yang, “Image restoration using very deep convolutional encoder-decoder networks with symmetric skip connections,” in *Proc. NIPS*, 2016.
O. Ronneberger, P. Fischer, and T. Brox, “U-Net: Convolutional networks for biomedical image segmentation,” in *Proc. MICCAI*, 2015, pp. 234–241.
S. Woo, J. Park, J.-Y. Lee, and I. S. Kweon, “CBAM: Convolutional block attention module,” in *Proc. ECCV*, 2018, pp. 3–19.
Q. Wang et al., “ECA-Net: Efficient channel attention for deep convolutional neural networks,” in *Proc. CVPR*, 2020, pp. 11534–11542.
Y. Qin, H. Lu, Y. Bai, and X. Wang, “Residual attention U-Net for automatic liver lesion segmentation,” *IEEE J. Biomed. Health Inform.*, vol. 24, no. 12, pp. 3411–3420, Dec. 2020.
R. C. Gonzalez and R. E. Woods, *Digital Image Processing*, 3rd ed. Upper Saddle River, NJ, USA: Prentice-Hall, 2008.
A. K. Jain, *Fundamentals of Digital Image Processing*, Prentice-Hall, 1989.
Y. Chen, L. Xu, and Z. Liu, “Deep hybrid attention network for image denoising,” *IEEE Access*, vol. 10, pp. 78054–78065, 2022.
X. Li, M. Yang, and H. Zhang, “Attention-based residual dense network for image restoration,” *Pattern Recognition Letters*, vol. 167, pp. 50–58, 2023.
G. Huang, Y. Chen, and X. Wang, “Edge-enhanced denoising with dual-domain attention,” in *Proc. ICPR*, 2021.
Y. Liu, X. Wang, and S. Shen, “Learnable fusion of channel and spatial attention for image restoration,” *Neurocomputing*, vol. 493, pp. 327–336, 2022.
O. Oktay et al., “Attention U-Net: Learning where to look for the pancreas,” *arXiv preprint arXiv:1804.03999*, 2018.
D. Zhang, L. Zhang, and X. Liu, “Noise-aware loss for image denoising under real noise conditions,” *IEEE TIP*, vol. 29, pp. 6081–6093, 2020.
Gonzalez, R. C., & Woods, R. E. (2022). *Digital Image Processing* (4th ed.). Pearson.
Khan, A., & Qureshi, M. A. (2023). Deep Learning Techniques for Image Processing: A Review. *Journal of Imaging*, 9(3), 45.
Ronneberger, O., Fischer, P., & Becker, A. (2015). U-Net: Convolutional networks for biomedical image segmentation. In *Medical Image Computing and Computer-Assisted Intervention* (Vol. 9351, pp. 234-241).
Farooq, Y., & Savaş, S. (2023). Noise removal from the image using convolutional neural networks-based denoising auto encoder. *Journal of Emerging Computer Technologies*, 3(1), 21-28.
Radke, K.L., Kamp, B., Adriaenssens, V., Stabinska, J., Gallinnis, P., Wittsack, H.-J., Antoch, G., & Müller-Lutz, A.(2023). Deep learning-based denoising of CEST MR data: A feasibility study on applying synthetic phantoms in medical imaging.
Bello, I., Zoph, B., & Vaswani, A. (2021). Attention mechanisms in deep learning: A survey. *IEEE Transactions on Neural Networks and Learning Systems*, 32(11), 4677-4696.
Mathew, I. M., Akhilaraj, D., & Zacharias, J. (2023). Speckle Noise Reduction in Satellite Images. In 2023 International Conference on Network, Multimedia and Information Technology (NMITCON). IEEE. https://doi.org/10.1109/NMITCON58196.2023.10275945
Kim, S., et al. (2020). Deep learning techniques for image quality enhancement in low-light conditions. *IEEE Transactions on Image Processing*, 29, 1234-1245.
Lohani, B., Gautam, C. K., Kushwaha, P., & Gupta, A. (2024). Deep Learning Approaches for Enhanced Audio Quality Through Noise Reduction. In 2024 International Conference on Communication, Computer Sciences and Engineering (IC3SE). IEEE. https://doi.org/10.1109/IC3SE62002.2024.10593073
Nazir, N., Sarwar, A., & Saini, B. (2024). Recent developments in denoising medical images using deep learning: An overview of models, techniques, and challenges. Micron. https://doi.org/10.1016/j.micron.2024.103615
Botnari, A., Kadar, M., & Patrascu, J. M. (2024). Considerations on Image Preprocessing Techniques Required by Deep Learning Models. The Case of the Knee MRIs. Mædica - a Journal of Clinical Medicine, 19(3), 526-535. doi:10.26574/maedica.2024.19.3.526. Available at: Mædica Journal 4.
Krizhevsky, A., Sutskever, I., & Hinton, G.E. (2012). ImageNet classification with deep convolutional neural networks. In *Advances in Neural Information Processing Systems* (Vol. 25).
Agustsson, E., & Timofte, R. (2021). NTIRE 2021 challenge on real-world super-resolution: Methods and results. In *Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops*.
Radke, K.L., Kamp, B., Adriaenssens, V., Stabinska, J., Gallinnis, P., Wittsack, H.-J., Antoch, G., & Müller-Lutz, A.(2023). Deep learning-based denoising of CEST MR data: A feasibility study on applying synthetic phantoms in medical imaging.
Izadi, S., Sutton D., & Hamarneh G.(2022). Image denoising in the deep learning era.
https://paperswithcode.com/dataset/cifar-10
Oktay, O., Schlemper, J., Le Folgoc, L., Lee, M., Heinrich, M., Misawa, K., Mori, K., McDonagh, S., Hammerla, N. Y., Kainz, B., Glocker, B., & Rueckert, D. (2018). Attention U-Net: Learning Where to Look for the Pancreas. Medical Image Computing and Computer-Assisted Intervention (MICCAI).
Downloads
Published
Submitted
Revised
Accepted
Issue
Section
License
Copyright (c) 2024 Kimia Peyvandi; Zahra Abbasi (Author)
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
