Home / Current Issue / Paper 1705971
Minimising Gaussian noise from real time CCTV images using GAN
Subject area: Science,Engineering and Technology · Area of research: Image Processing using Deep Learning
Abstract
This paper describes a system that uses generative adversarial networks (GANs) to eliminate gaussian noise from CCTV images. Unwanted noise like gaussian noise frequently degrades the quality of images and makes them more difficult to interpret. In our approach, a discriminator network is used to direct the training of a generator network, whose job it is to produce denoised images from noisy inputs. This framework includes operations like picture enhancement, noise reduction, and evaluation with metrics like the structural similarity index (SSIM) and peak signal-to-noise ratio (PSNR). The resultant denoised images show enhanced visual quality and have potential uses in image analysis and computer vision.
Keywords
Generative Adversarial Networks (GANs), Image Interpretation, Noise Removal, Visual Quality Improvement
References
[1] Abeer Alsaiari, Ridhi Rustagi, Manu Mathew Thomas, Angus G Forbes, et al. Image denoising using a generative adversarial network. In 2019 IEEE 2nd international conference on information and computer technologies (ICICT), pages 126–132. IEEE, 2019.
[2] Miao Tian and Kaikai Song. Boosting magnetic resonance image denoising with generative adversarial networks. IEEE Access, 9:6226662275, 2021.
[3] Xintao Wang, Liangbin Xie, Chao Dong, and Ying Shan. Real-esrgan: Training real-world blind super-resolution with pure synthetic data. In Proceedings of the IEEE/CVF international conference on computer vision, pages 1905–1914, 2021.
[4] Qingsong Yang, Pingkun Yan, Yanbo Zhang, Hengyong Yu, Yongyi Shi, Xuanqin Mou, Mannudeep K Kalra, Yi Zhang, Ling Sun, and Ge Wang. Low-dose ct image denoising using a generative adversarial network with wasserstein distance and perceptual loss. IEEE transactions on medical imaging, 37(6):1348–1357, 2018.
[5] Qu ZhiPing, Zhang YuanQi, Sun Yi, and Lin XiangBo. A new generative adversarial network for texture preserving image denoising. In 2018 Eighth International Conference on Image Processing Theory, Tools and Applications (IPTA), pages 1–5. IEEE, 2018.
[6] Liqun Zhong, Guole Liu, and Ge Yang. Blind denoising of fluorescence microscopy images using gan-based global noise modeling. In 2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI), pages 863867. IEEE, 2021.
How to cite this paper
@article{1705971,
author = {Pranava Aithal K S, Akshay Prashant Hegde, Adyapadi Suraj},
title = {Minimising Gaussian noise from real time CCTV images using GAN},
journal = {Iconic Research And Engineering Journals},
year = {2024},
volume = {7},
number = {12},
pages = {384-393},
issn = {2456-8880},
url = {https://www.irejournals.com/formatedpaper/1705971.pdf},
abstract = {This paper describes a system that uses generative adversarial networks (GANs) to eliminate gaussian noise from CCTV images. Unwanted noise like gaussian noise frequently degrades the quality of images and makes them more difficult to interpret. In our approach, a discriminator network is used to direct the training of a generator network, whose job it is to produce denoised images from noisy inputs. This framework includes operations like picture enhancement, noise reduction, and evaluation with metrics like the structural similarity index (SSIM) and peak signal-to-noise ratio (PSNR). The resultant denoised images show enhanced visual quality and have potential uses in image analysis and computer vision.},
keywords = {Generative Adversarial Networks (GANs), Image Interpretation, Noise Removal, Visual Quality Improvement},
month = {June},
}