Image denoising based on deep feature fusion and U-Net network

Yong  Zhang

doi:10.6180/jase.202510_28(10).0020

Image denoising based on deep feature fusion and U-Net network

Computer Science and Information Engineering

Yong ZhangThis email address is being protected from spambots. You need JavaScript enabled to view it.

Software College, Shenyang Normal University Shenyang 110034 China

Received: November 12, 2024
Accepted: December 21, 2024
Publication Date: February 27, 2025

Copyright The Author(s). This is an open access article distributed under the terms of the Creative Commons Attribution License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are cited.

Download Citation: ||https://doi.org/10.6180/jase.202510_28(10).0020

Image noise hinders the understanding of images by advanced visual tasks, and removing image noise is a challenging task. The traditional denoising methods can not only destroy the texture of the image, but can not save the image texture after removing the noise. Therefore, we propose a novel image denoising method based on deep feature fusion and U-Net network. This new method uses a two-branch U-Net network to fuse features and preserve image texture. In this paper, two encoders with independent parameters are proposed to extract more useful information respectively, and a fusion module with series connection is proposed to make better use of the extracted information and remove redundant information. Finally, the decoder is used to reconstruct the image, and the U-Net peer connection is used on the symmetric convolutional layer in the network. A large number of experimental results show that the proposed algorithm can effectively remove synthetic noise and real noise, and the reconstructed image has a good effect on both subjective visual effect and objective evaluation index.

Keywords: Image denoising, deep feature fusion, U-Net network, symmetric convolutional layer

[1] Y. Li, G. Liu, D. P. Bavirisetti, X. Gu, and X. Zhou, (2023) “Infrared-visible image fusion method based on sparse and prior joint saliency detection and LatLRR FPDE" Digital Signal Processing 134: 103910. DOI: 10.1016/j.dsp.2023.103910.
[2] L.Teng,Y. Qiao, M.Shafiq, G. Srivastava, A. R. Javed, T. R. Gadekallu, and S. Yin, (2023) “FLPK-BiSeNet: Federated learning based on priori knowledge and bilateral segmentation network for image edge extraction" IEEE Transactions on Network and Service Management 20(2): 1529–1542. DOI: 10.1109/TNSM.2023.3273991.
[3] X. Meng, X. Wang, S. Yin, and H. Li, (2023) “Few-shot image classification algorithm based on attention mecha nism and weight fusion" Journal of Engineering and Applied Science 70(1): 14. DOI: 10.1186/s44147-023 00186-9.
[4] S. Wang, L. Li, X. Li, J. Zhang, L. Zhao, X. Su, and F. Chen, (2023) “A denoising network based on frequency spectral-spatial-feature for hyperspectral image" IEEE Journal of Selected Topics in Applied Earth Ob servations and Remote Sensing 16: 6693–6710. DOI: 10.1109/JSTARS.2023.3285454.
[5] A.Ulu,G.Yildiz, and B. Dizdaro˘ glu, (2023) “MLFAN: Multilevel Feature Attention Network With Texture Prior for Image Denoising" IEEE Access 11: 34260–34273.
[6] Z. Li, H. Liu, L. Cheng, and X. Jia, (2023) “Image denoising algorithm based on gradient domain guided f iltering and NSST" IEEE Access 11: 11923–11933. DOI: 10.1109/ACCESS.2023.3242050.
[7] A. M. H. Abadi and M. R. H. Fatemi, (2023) “Itera tive based image and video denoising by fractional block matching and transform domain filtering" Authorea Preprints:
[8] K. Dabov, A. Foi, V. Katkovnik, and K. Egiazarian, (2007) “Image denoising by sparse 3-D transform-domain collaborative filtering" IEEE Transactions on image processing 16(8): 2080–2095. DOI: 10.1109/TIP.2007.901238.
[9] S. Yin, H. Li, Y. Sun, M. Ibrar, and L. Teng, (2024) “Data Visualization Analysis Based on Explainable Arti f icial Intelligence: A Survey" IJLAI Transactions on Science and Engineering 2(2): 13–20.
[10] S. Yin, H. Li, A. A. Laghari, T. R. Gadekallu, G. A. Sampedro, and A. Almadhor, (2024) “An anomaly detection model based on deep auto-encoder and capsule graph convolution via sparrow search algorithm in 6G internet-of-everything" IEEE Internet of Things Jour nal 11(18): 13–20. DOI: 10.1109/JIOT.2024.3353337.
[11] H.Li and C. Zhao, (2024) “Fusion Cycle GAN: A Mul tiple Feature Fusion based Cycle-consistent Generative Adversarial Network for Person Re-Identification" Jour nal of Science and Engineering 1(1): 7–12.
[12] X.Mao,C.Shen,andY.-B. Yang, (2016) “Image restora tion using very deep convolutional encoder-decoder net works with symmetric skip connections" Advances in neural information processing systems 29: 2810–2818.
[13] C.Shan,X.Guo,andJ.Ou,(2019)“Residuallearning of deep convolutional neural networks for image denoising" Journal of Intelligent & Fuzzy Systems 37(2): 2809 2818. DOI: 10.3233/JIFS-190017.
[14] Y. Li, Y. Wang, and N. Wu, (2021) “Noise suppression methodbased onmulti-scale Dilated Convolution Network in desert seismic data" Computers & Geosciences 156: 104910. DOI: 10.1016/j.cageo.2021.104910.
[15] S.Lee, M.Negishi, H. Urakubo, H. Kasai, and S. Ishii, (2020) “Mu-net: Multi-scale U-net for two-photon mi croscopy image denoising and restoration" Neural Net works 125: 92–103. DOI: 10.1016/j.neunet.2020.01.026.
[16] X. Wu, K. Zhang, Y. Hu, X. He, and X. Gao, (2024) “Multi-scale non-local attention network for image super resolution" Signal Processing 218: DOI: 10.1016/j.sigpro.2023.109362.
[17] S.Yin,L.Wang,M.Shafiq,L.Teng,A.A.Laghari,and M. F. Khan, (2023) “G2Grad-CAMRL: an object detec tion and interpretation model based on gradient-weighted class activation mapping and reinforcement learning in remote sensing images" IEEE Journal of Selected Top ics in Applied Earth Observations and Remote Sensing 16: 3583–3598. DOI: 10.1109/JSTARS.2023.3241405.
[18] Y. Chen and T. Pock, (2016) “Trainable nonlinear reac tion diffusion: A flexible framework for fast and effective image restoration" IEEE transactions on pattern anal ysis and machine intelligence 39(6): 1256–1272. DOI: 10.1109/TPAMI.2016.2596743.
[19] G. Cheng, A. Matsune, Q. Li, L. Zhu, H. Zang, and S. Zhan. “Encoder-decoder residual network for real super-resolution”. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. 2019. DOI: 10.1109/CVPRW.2019.00270.
[20] X. Deng and P. L. Dragotti, (2020) “Deep convolu tional neural network for multi-modal image restoration and fusion" IEEE transactions on pattern analysis and machine intelligence 43(10): 3333–3348. DOI: 10.1109/TPAMI.2020.2984244.
[21] K. Zhang, W. Zuo, and L. Zhang, (2018) “FFDNet: Toward a fast and flexible solution for CNN-based image denoising" IEEE Transactions on Image Processing 27(9): 4608–4622. DOI: 10.1109/TIP.2018.2839891.
[22] R. Ma, S. Li, B. Zhang, and Z. Li, (2021) “Towards fast and robust real image denoising with attentive neu ral network and PID controller" IEEE Transactions on Multimedia 24: 2366–2377. DOI: 10.1109/TMM.2021. 3079697.
[23] D.HonzátkoandM.Kruliš,(2019) “Accelerating block matching and 3D filtering method for image denoising on GPUs" Journal of Real-Time Image Processing 16(6): 2273–2287. DOI: 10.1007/s11554-017-0737-9.
[24] R. Kaftory, Y. Y. Schechner, and Y. Y. Zeevi. “Vari ational distance-dependent image restoration”. In: 2007 IEEE conference on computer vision and pattern recognition. IEEE. 2007, 1–8. DOI: 10.1109/CVPR.2007.383262.
[25] T. Ma, H. Zhou, Y. Tian, and N. Al-Nabhan, (2021) “A novel rumor detection algorithm based on entity recog nition, sentence reconfiguration, and ordinary differen tial equation network" Neurocomputing 447: 224–234. DOI: 10.1016/j.neucom.2021.03.055.