Academic Journal of Computing & Information Science, 2024, 7(7); doi: 10.25236/AJCIS.2024.070702.
Yuan Chen1, Yun Yang1, Palizhati·Wusiman1, Yanan Wu2, Hong Yang3
1School of Electronic Information and Artificial Intelligence, Shaanxi University of Science and Technology, Xi'an, Shaanxi, China
2Xi'an Institute of Metrology Technology, Quality Management Department, Xi'an, Shaanxi, China
3Xi'an Fude Medical Electronics Co., Ltd., Quality Management Department, Xi'an, Shaanxi, China
In response to the issues of excessive smoothing and detail loss in existing image denoising algorithms, a dual-channel image denoising algorithm based on deformable convolution is proposed. Firstly, a noise estimation network is used to obtain a noise level map, enhancing the detail preservation capability of the edge feature extraction block enhancement network. Then, efficient channel attention is combined to focus on key channel features, effectively capturing noise characteristics. Finally, the deformable convolution with deformable learning kernels is integrated into the dual-channel denoising network to extract offset pixels of feature mappings, avoiding excessive image smoothing. Experimental results show that on the Set12 dataset with a noise level of 25, compared with commonly used algorithms, the proposed algorithm improves the average peak signal-to-noise ratio and structural similarity by 0.08dB to 0.62dB and 0.001 to 0.02, respectively, while removing Gaussian noise and preserving image details as much as possible.
Image denoising; Dense block; Feature extraction; Attention mechanism
Yuan Chen, Yun Yang, Palizhati·Wusiman, Yanan Wu, Hong Yang. Research on Dual-Channel Image Denoising Algorithm Based on Deformable Convolution. Academic Journal of Computing & Information Science (2024), Vol. 7, Issue 7: 9-16. https://doi.org/10.25236/AJCIS.2024.070702.
[1] C. Tian, L. Fei, W. Zheng, et al. Deep learning on image denoising: An overview[J]. Neural Networks, 2020, 131: 251–275.
[2] Zhang Q, Xiao J, Tian C, et al. A robust deformed convolutional neural network (CNN) for image denoising [J]. CAAI Transactions on Intelligence Technology, 2023, 8(2): 331-342.
[3] K. Zhang, W. Zuo, Y. Chen, et al. Beyond a gaussian denoiser: Residual learning of deep CNN for image denoising[J]. IEEE Transactions on Image Processing, 2017, 26 (7): 3142–3155.
[4] Zhang K, Zuo W, Zhang L. FFDNet: Toward a fast and flexible solution for CNN-based image denoising [J]. IEEE Transactions on Image Processing, 2018, 27(9): 4608-4622.
[5] Guo S, Yan Z, Zhang K, et al. Toward convolutional blind denoising of real photo graphs[C]. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019: 1712-1722.
[6] TIAN C, XU Y, LI Z, et al. Attention-guided CNN for image denoising[J]. Neural Networks, 2020, 124: 117-129.
[7] TIAN C, XU Y, ZUO W. Image denoising using deep CNN with batch renormalization[J]. Neural Networks, 2020, 121:461-473.
[8] TIAN C, XU Y, ZUO W, et al. Designing and trainingofa dual CNN forimage denoising[J]. Knowledge-Based Systems, 2021, 226:106949.
[9] Wang, Q., Wu, B., Zhu, P. et al. Eca-net: Efficient channel attention for deep convolutional neural networks[J]. IEEE Conference on Computer Vision and Pattern Recognition (CVPR),2020.
[10] W. Lai, J. Huang, N. Ahuja, et al. Deep laplacian pyramid networks for fast and accurate super-resolution[J]. IEEE Conference on Computer Vision and Pattern Recognition, 2017, 624–632.
[11] K. Jiang, Z. Wang, P. Yi, et al. Multi-scale progressive fusion network for single image deraining[J]. IEEE Conference on Computer Vision and Pattern Recognition, 2020, 8346–8355.
[12] S. Guo, Z. Yan, K. Zhang, et al. Toward convolutional blind denoising of real photographs[J]. IEEE Conference on Computer Vision and Pattern Recognition, 2019, 1712–1722.
[13] Mahdaoui A E, Ouahabi A, Moulay M S. Image denoising using a compressive sensing approach based on regularization constraints[J]. Sensors, 2022, 22(6): 2199.
[14] AGUSTSSON E, TIMOFTE R. NTIRE 2017 Challenge on Single Image Super-Resolution: Dataset and Study[C]. IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2017, 1122–1131.