{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,24]],"date-time":"2025-11-24T12:48:09Z","timestamp":1763988489041,"version":"3.45.0"},"reference-count":30,"publisher":"National Library of Serbia","issue":"4","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["ComSIS","COMPUT SCI INF SYST","COMPUT SCI INFORM SY","COMPUTER SCI INFORM","COMSIS J"],"published-print":{"date-parts":[[2025]]},"abstract":"<jats:p>Although many models that have applied learning exhibit good performance, the dataset or image generation and transmission process used for learning may contain noise, which cannot produce the expected results and performance. The representative image denoising technique using deep neural networks generates noisy images by forcibly adding special noise to the original image and learning to make it the same as the original image. However, the performance of deep neural networks depends on depth, and to improve performance, increasing only depth will reach a performance saturation state, which will encounter difficulties. In order to improve these issues, this article applies the Multi-scale Attention model to the representative denoising deep learning model U-Net, to suppress unnecessary information and provide functionality that only emphasizes important information. In a new modular approach, the given input value is divided into two parts based on its internal relationship: the part where the important parts are concentrated and the part where the important parts are concentrated through spatial information. The attention unit based Outburst structure, which combines the two parts after parallel execution, has been implemented, demonstrating better performance than existing models. Moreover, without adding too many parameters, more spatial feature maps than other models are generated by focusing on the effects of components, not only through PSNR and SSIM. The improved performance was also confirmed by removing noisy in images.<\/jats:p>","DOI":"10.2298\/csis240810064a","type":"journal-article","created":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T12:38:46Z","timestamp":1759235926000},"page":"1617-1636","source":"Crossref","is-referenced-by-count":0,"title":["A study on multi-scale attention dense U-Net for image denoising method"],"prefix":"10.2298","volume":"22","author":[{"given":"MingShou","family":"An","sequence":"first","affiliation":[{"name":"Dong-A University, Dept. of Electronics Engineering, Nakdong-daero, beon-gil Saha-gu, Busan, Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuhang","family":"Zhao","sequence":"additional","affiliation":[{"name":"Dong-A University, Dept. of Electronics Engineering, Nakdong-daero, beon-gil Saha-gu, Busan, Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hye-Youn","family":"Lim","sequence":"additional","affiliation":[{"name":"Dong-A University, Dept. of Electronics Engineering, Nakdong-daero, beon-gil Saha-gu, Busan, Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dae-Seong","family":"Kang","sequence":"additional","affiliation":[{"name":"Dong-A University, Dept. of Electronics Engineering, Nakdong-daero, beon-gil Saha-gu, Busan, Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1078","reference":[{"key":"ref1","doi-asserted-by":"crossref","unstructured":"F. Emmert-Streib, Z. Yan, H. Feng, S. Tripathi, and M. Dehmer.: An Introductory Review of Deep Learning for Prediction Models With Big Data, Frontiers in Artificial Intelligence, Vol. 3, pp. 4, Feb. 2020.","DOI":"10.3389\/frai.2020.00004"},{"key":"ref2","doi-asserted-by":"crossref","unstructured":"Shanthi, T., and R. S. Sabeenian.: Modified Alexnet architecture for classification of diabetic retinopathy images, Computers and Electrical Engineering, Vol. 76, pp. 56-64, 2019.","DOI":"10.1016\/j.compeleceng.2019.03.004"},{"key":"ref3","doi-asserted-by":"crossref","unstructured":"Majib, Mohammad Shahjahan, et al.: Vgg-scnet: A vgg net-based deep learning framework for brain tumor detection on mri images.\u201d IEEE Access 9, pp. 116942-116952, 2021.","DOI":"10.1109\/ACCESS.2021.3105874"},{"key":"ref4","doi-asserted-by":"crossref","unstructured":"Tang, Pengjie, Hanli Wang, and Sam Kwong.: G-MS2F: GoogLeNet based multi-stage feature fusion of deep CNN for scene recognition, Neurocomputing, Vol. 225, pp. 188-197, 2017.","DOI":"10.1016\/j.neucom.2016.11.023"},{"key":"ref5","unstructured":"Wightman, Ross, Hugo Touvron, and Herv\u00e9 J\u00e9gou.: Resnet strikes back: An improved training procedure in timm, arXiv preprint arXiv:2110.00476, 2021."},{"key":"ref6","doi-asserted-by":"crossref","unstructured":"Arkin, Ershat, et al.: A survey: object detection methods from CNN to transformer, Multimedia Tools and Applications Vol. 82, No. 14, pp. 21353-21383, 2023.","DOI":"10.1007\/s11042-022-13801-3"},{"key":"ref7","doi-asserted-by":"crossref","unstructured":"C. Tian, Y. Xu, and W. Zuo.: Image denoising using deep CNN with batch renormalization, ISSN, Vol 121, pp. 461-473, Jan. 2020.","DOI":"10.1016\/j.neunet.2019.08.022"},{"key":"ref8","unstructured":"J. Lehtinen, J. Munkberg, J. Hasselgren, S. Laine, T. Karras, M. Aittala, and T. Aila.: Noise2Noise: Learning Image Restoration without Clean Data, International Conference on Machine Learning, ICML, Vol. 7, No. 12, pp. 4620-4631, Jan. 2018."},{"key":"ref9","doi-asserted-by":"crossref","unstructured":"Li, Zhuo, Hengyi Li, and Lin Meng.: Model compression for deep neural networks: A survey, Computers, Vol. 12, No. 3, pp. 60, 2023.","DOI":"10.3390\/computers12030060"},{"key":"ref10","doi-asserted-by":"crossref","unstructured":"Yan, Puti, et al.: STDMANet: Spatio-temporal differential multiscale attention network for small moving infrared target detection, IEEE transactions on geoscience and remote sensing, Vol. 61, pp. 1-16.","DOI":"10.1109\/TGRS.2023.3241311"},{"key":"ref11","doi-asserted-by":"crossref","unstructured":"Zhu, Junqi, et al.: Evaluation of deep coal and gas outburst based on RS-GA-BP, Natural Hazards, Vol. 115, No. 3, pp. 2531-2551, 2023.","DOI":"10.1007\/s11069-022-05652-w"},{"key":"ref12","doi-asserted-by":"crossref","unstructured":"Murali, Vineeth, and P. V. Sudeep.: Image denoising using DnCNN: An exploration study, Advances in Communication Systems and Networks: Select Proceedings of ComNet 2019, pp. 847-859, 2020.","DOI":"10.1007\/978-981-15-3992-3_72"},{"key":"ref13","doi-asserted-by":"crossref","unstructured":"Shafiq, Muhammad, and Zhaoquan Gu.: Deep residual learning for image recognition: A survey, Applied Sciences, Vol. 12, No. 18, pp. 8972, 2022.","DOI":"10.3390\/app12188972"},{"key":"ref14","doi-asserted-by":"crossref","unstructured":"Garbin, Christian, Xingquan Zhu, and Oge Marques.: Dropout vs. batch normalization: an empirical study of their impact to deep learning, Multimedia tools and applications, Vol. 79, No. 19, pp. 12777-12815, 2020.","DOI":"10.1007\/s11042-019-08453-9"},{"key":"ref15","unstructured":"danielseo, \u201c[Computer Vision] DnCNN\u201d, gihyun.log, Jun 2021, https:\/\/velog.io\/@danielseo\/Computer-Vision-DnCNN."},{"key":"ref16","doi-asserted-by":"crossref","unstructured":"Niu, Zhaoyang, Guoqiang Zhong, and Hui Yu.: A review on the attention mechanism of deep learning, Neurocomputing, Vol. 452, pp. 48-62, 2021.","DOI":"10.1016\/j.neucom.2021.03.091"},{"key":"ref17","doi-asserted-by":"crossref","unstructured":"Ren, Zhongzheng, et al.: Instance-aware, context-focused, and memory-efficient weakly supervised object detection, Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, 2020.","DOI":"10.1109\/CVPR42600.2020.01061"},{"key":"ref18","doi-asserted-by":"crossref","unstructured":"Li, Xiaohui, Haiying Xia, and Lidan Lu.: ECA-CBAM: Classification of Diabetic Retinopathy: Classification of diabetic retinopathy by cross-combined attention mechanism, Proceedings of the 2022 6th international conference on innovation in artificial intelligence, 2022.","DOI":"10.1145\/3529466.3529468"},{"key":"ref19","doi-asserted-by":"crossref","unstructured":"Siddique, Nahian, et al.: U-net and its variants for medical image segmentation: A review of theory and applications, IEEE Access, Vol. 9, pp. 82031-82057, 2021.","DOI":"10.1109\/ACCESS.2021.3086020"},{"key":"ref20","doi-asserted-by":"crossref","unstructured":"Wu, Jizhong, et al.: Fault detection based on fully convolutional networks (FCN), Journal of Marine Science and Engineering, Vol. 9, No. 3, pp. 259, 2021.","DOI":"10.3390\/jmse9030259"},{"key":"ref21","doi-asserted-by":"crossref","unstructured":"Yin, Haitao, and Siyuan Ma.: CSformer: Cross-scale features fusion based transformer for image denoising, IEEE Signal Processing Letters, Vol. 29, pp. 1809-1813, 2022.","DOI":"10.1109\/LSP.2022.3199145"},{"key":"ref22","doi-asserted-by":"crossref","unstructured":"Yahya, Ali Abdullah, et al.: BM3D image denoising algorithm based on an adaptive filtering, Multimedia Tools and Applications, Vol. 79, pp. 20391-20427, 2020.","DOI":"10.1007\/s11042-020-08815-8"},{"key":"ref23","doi-asserted-by":"crossref","unstructured":"Yu, Qiqiong, et al.: EPLL image denoising with multi-feature dictionaries, Digital Signal Processing, Vol. 137, pp. 104019, 2023.","DOI":"10.1016\/j.dsp.2023.104019"},{"key":"ref24","doi-asserted-by":"crossref","unstructured":"Uetani, Hiroyuki, et al.: A preliminary study of deep learning-based reconstruction specialized for denoising in high-frequency domain: usefulness in high-resolution three-dimensional magnetic resonance cisternography of the cerebellopontine angle, Neuroradiology, Vol.63, pp. 63-71, 2021.","DOI":"10.1007\/s00234-020-02513-w"},{"key":"ref25","unstructured":"Averbuch, Amir, et al.: Cross-boosting of WNNM image denoising method by directional wavelet packets, arXiv preprint arXiv:2206.04431, 2022."},{"key":"ref26","doi-asserted-by":"crossref","unstructured":"Jia, Nan, et al.: Background noise suppression using trainable nonlinear reaction diffusion assisted by robust principal component analysis.\u201d Exploration Geophysics, Vol. 51, No. 6, pp. 642-651, 2020.","DOI":"10.1080\/08123985.2020.1738212"},{"key":"ref27","doi-asserted-by":"crossref","unstructured":"Zou, Xueyan, et al.: Intelligent diagnosis method of bearing fault based on ICEEMDAN and Ghost-IRCNN, Proceedings of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science, Vol. 237, No. 13, pp. 3115-3130, 2023.","DOI":"10.1177\/09544062221144390"},{"key":"ref28","doi-asserted-by":"crossref","unstructured":"Cao, Like, Jie Ling, and Xiaohui Xiao.: Study on the influence of image noise on monocular feature-based visual slam based on ffdnet, Sensors, Vol. 20, No. 17, pp. 4922, 2020.","DOI":"10.3390\/s20174922"},{"key":"ref29","doi-asserted-by":"crossref","unstructured":"Qi, Huiqing, Shengli Tan, and Zhichao Li.: Anisotropic weighted total variation feature fusion network for remote sensing image denoising, Remote Sensing, Vol. 14, No. 24, pp. 6300, 2022.","DOI":"10.3390\/rs14246300"},{"key":"ref30","doi-asserted-by":"crossref","unstructured":"Liu, Zhen, et al.: ADNet: Attention-guided deformable convolutional network for high dynamic range imaging.\u201d Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021.","DOI":"10.1109\/CVPRW53098.2021.00057"}],"container-title":["Computer Science and Information Systems"],"original-title":[],"language":"en","deposited":{"date-parts":[[2025,11,24]],"date-time":"2025-11-24T12:34:58Z","timestamp":1763987698000},"score":1,"resource":{"primary":{"URL":"https:\/\/doiserbia.nb.rs\/Article.aspx?ID=1820-02142500064A"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":30,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2025]]}},"URL":"https:\/\/doi.org\/10.2298\/csis240810064a","relation":{},"ISSN":["1820-0214","2406-1018"],"issn-type":[{"type":"print","value":"1820-0214"},{"type":"electronic","value":"2406-1018"}],"subject":[],"published":{"date-parts":[[2025]]}}}