MECHANISMS FOR IMPROVING THE QUALITY AND DENOISING OF IMAGES BASED ON THE CONVOLUTION AND RECURRENT NEURAL NETWORKS

DOI: 10.31673/2412-4338.2023.018289

Abstract

This article provides an overview of methods for image enhancement and denoising based on convolutional and recurrent neural networks with the addition of a non-local operations block. These methods are widely used in various domains. In medicine, these methods improve MRI images, assisting doctors in making accurate diagnoses. In security applications, these approaches enhance images and enable better visualization of details. The article covers the main existing approaches to image enhancement.
The article presents an analysis of the key characteristics of the investigated neural networks, as well as the scenarios in which they are most effective. It also includes a table of results from several image enhancement methods and introduces a research method for comparing its effectiveness in image enhancement. The strengths of each approach are highlighted, and their efficiency in different scenarios is discussed. Considering specific characteristics of denoising tasks such as noise patterns, image types, and processing constraints can help in selecting the most suitable architecture to achieve the desired outcome. The article also highlights the use of the non-local operations block to improve image quality. This block is used to capture global dependencies among pixels, allowing better modeling of relationships between different parts of the image. The non-local operations block enables efficient detection of long-range dependencies and contextual information, leading to improved denoising and image restoration.
Overall, this article is useful for researchers in the field of image processing and machine learning who are interested in understanding the key differences between convolutional neural networks (CNNs) and recurrent neural networks (RNNs) and exploring existing approaches to image enhancement and denoising. It provides a comprehensive overview of methods for image enhancement and denoising using convolutional and recurrent neural networks with the addition of a non-local operations block, along with information about existing approaches. The information and recommendations presented in this article can assist in selecting appropriate methods for addressing image processing tasks.

Keywords: Convolutional and recurrent neural networks, Non-local operations, improvement of images.

References:
1. Chao Dong, Chen Change Loy, Member, IEEE, Kaiming He, Member, IEEE, and Xiaoou Tang, Fellow, IEEE Image Super-Resolution Using Deep Convolutional Networks. 2015. https://arxiv.org/pdf/1501.00092.pdf (accessed 06/15/2023).
2. Kai Zhang, Wangmeng Zuo, Lei Zhang Learning a Single Convolutional Super-Resolution Network for Multiple Degradations. 2018. https://openaccess.thecvf.com/content_cvpr_2018/papers/Zhang_Learning_a_Single_CVPR_2018_paper.pdf (accessed 15/06/2023).
3. Wang et al Non-Local Operation. 2018. https://paperswithcode.com/method/non-local-operation
4. Stamatios Lefkimmiatis Non-local Color Image Denoising with Convolutional Neural Networks. 2016. https://arxiv.org/pdf/1611.06757.pdf (accessed 06/15/2023).
5. Xiaolong Wang, Ross Girshick, Abhinav Gupta, Kaiming He Non-local Neural Networks. 2018 https://arxiv.org/pdf/1711.07971.pdf (date of access: 15/06/2023).
6. Ding Liu, Bihan Wen, Yuchen Fan, Chen Change Loy, Thomas S. Huang Non-Local Recurrent Network for Image Restoration. 2018. https://proceedings.neurips.cc/paper_files/paper/2018/file/fc49306d97602c8ed1be1dfbf0835ead-Paper.pdf (accessed 15/06/2023).
7. Chunwei Tian, Lunke Fei, Wenxian Zheng, Yong Xu, Wangmeng Zuo, Chia-Wen Lin Deep Learning on Image Denoising: An Overview. 2019. https://arxiv.org/pdf/1912.13171.pdf (accessed 06/15/2023).
8. Bohdan V. Chapaliuk, Yuriy P. Zaychenko Using recurrent neural networks for automatic diagnosis of lung cancer. 2019 http://journal.iasa.kpi.ua/article/view/177906 (access date: 06/15/2023).
9. Zinchenko O. V., Zvenigorodskyi O. S., Kysil T. M., Convolutional neural networks for solving computer vision problems. 2022. http://tit.dut.edu.ua/index.php/telecommunication/article/view/2417 (date of access: 15.06.2023).
10. Mykhaylov, V. S., Research and development of image enhancement methods. 2019. http://openarchive.nure.ua/handle/document/11968
11. Anakhov P., Zhebka V., Berkman L., Koretska V. Increasing Functional Stability of Telecommunications Network in the Depressed Zone of HPS Reservoir / Lecture Notes in Electrical Engineering, 2023, 965 LNEE, p. 214–230.