Surveillance Image Super Resolution Using SR - Generative Adversarial Network

Abstract:

A single-image-super-resolution (SISR) is the process of converting a single low-quality (LR) image to a high-quality (HR) image. This technology is utilised in a variety of industries, including medical and satellite imaging, to retrieve quality and required information from blurred or overexposed photos. Because of the lack of ability to extract important data and images due to poor quality surveillance photographs, this method can be utilised in the field of surveillance to produce high-quality images. We'd like to use General Adversarial Networks to handle low-quality photos because existing methods have resulted in slightly fuzzy and greasy images that look like oil paintings (GAN). We'd like to introduce Super Resolution General Adversarial Networks in particular (SRGAN). This method employs perceptual losses. In this case, PSNR, MSE, and SSIM values are shown to be superior to those obtained by standard approaches in this case. The SRGAN-processed photos are of excellent quality, allowing the images to be seen through hazy and misty areas.

• Periodical: Advances in Science and Technology (Volume 124)
• Pages: 125-136
• DOI: https://doi.org/10.4028/p-tj6e43
• Online since: February 2023
• Authors: N. Venkat Narayanan*, T. Arjun, R. Logeshwari
• Keywords: Generative Adversarial Network, Image Super Resolution, MSE, Peak Signal to Noise Ratio, SISR, SRGAN, SSIM, Surveillance

References

[1] Y. Wen, B. Sheng, P. Li, W. Lin and D. D. Feng, Deep Color Guided Coarse-to-Fine Convolutional Network Cascade for Depth Image Super-Resolution,, in IEEE Transactions on Image Processing, vol. 28, no. 2, pp.994-1006, Feb. (2019).

DOI: 10.1109/tip.2018.2874285

[2] W. Symolon and C. H. Dagli, Single-Image Super Resolution using Convolutional Neural Network,, Procedia Computer Science, vol. 185, pp.213-222, Elsevier B. V., Jun (2021).

DOI: 10.1016/j.procs.2021.05.022

[3] Sobhan Kanti Dhara, Debashis Sen,Across-scale process similarity based interpolation for image super-resolution,Applied Soft Computing, ,Volume 81,August 2019,105508.

DOI: 10.1016/j.asoc.2019.105508

[4] X. Xue, X. Zhang, H. Li and W. Wang, Research on GAN-based Image Super-Resolution Method,, 2020 IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA), 2020, pp.602-605.

DOI: 10.1109/icaica50127.2020.9182617

[5] M. Cao, Z. Liu, X. Huang and Z. Shen, Research for Face Image Super-Resolution Reconstruction Based on Wavelet Transform and SRGAN,, 2021 IEEE 5th Advanced Information Technology, Electronic and Automation Control Conference (IAEAC), 2021, pp.448-451.

DOI: 10.1109/iaeac50856.2021.9390748

[6] Purab Alok Jain , Pranali K. Kosamkar,Analysis and Prediction of COVID-19 with Image Super-Resolution Using CNN and SRCNN-Based Approach,, Vol. 248, Jan 2022,pp.33-40.

DOI: 10.1007/978-981-16-4177-0_5

[7] Yitong Yan, Chuangchuang Liu, Changyou Chen, Xianfang Sun, Longcun Jin, Xiang Zhou. Fine-grained Attention and Feature-sharing Generative Adversarial Networks for Single Image Super-Resolution. arXiv preprint arXiv:1911.10773, (2019).

DOI: 10.1109/tmm.2021.3065731

[8] S. Liu et al., Infrared Image Super Resolution Using GAN With Infrared Image Prior,, 2019 IEEE 4th International Conference on Signal and Image Processing (ICSIP), 2019, pp.1004-1009.

DOI: 10.1109/siprocess.2019.8868566

[9] A. A. Tandale and N. D. Kulkarni, Super-Resolution of Color Images Using CNN,, 2018 Second International Conference on Intelligent Computing and Control Systems (ICICCS), 2018, pp.1-5.

DOI: 10.1109/iccons.2018.8663215

[10] N. T. Man and T. Q. Vinh, Image Super-Resolution Using Image Registration and Neural Network Based Interpolation,, 2016 International Conference on Advanced Computing and Applications (ACOMP), 2016, pp.164-167.

DOI: 10.1109/acomp.2016.032

[11] A. Horé and D. Ziou, Image Quality Metrics: PSNR vs. SSIM,, 2010 20th International Conference on Pattern Recognition, 2010, pp.2366-2369.

DOI: 10.1109/icpr.2010.579

[12] Feng Zhou, Yong Hu, Xukun Shen,Advances in Multimedia Information Processing – PCM 2018,, Springer Science and Business Media LLC, 2018, Vol. 11166.

[13] C. Ledig et al., Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network,, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, pp.105-114.

DOI: 10.1109/cvpr.2017.19

[14] X. Zhong, Y. Wang, A. Cai, N. Liang, L. Li and B. Yan, Dual-Energy CT Image Super-resolution via Generative Adversarial Network,, 2021 International Conference on Artificial Intelligence and Electromechanical Automation (AIEA), 2021, pp.343-347.

DOI: 10.1109/aiea53260.2021.00079

[15] Yuxin PengShi-Min HuMoncef GabboujKun ZhouMichael EladKun Xu,Image and Graphics,,2021, Volume 12888.

[16] Li Chen, Jing Tian,Depth image enlargement using an evolutionary approach,,Signal Processing: Image Communication,Volume 28, Issue 7, August 2013, Pages 745-752.

DOI: 10.1016/j.image.2013.03.005

[17] Z. Wang, D. Liu, J. Yang, W. Han, and T. Huang, Deep networks for image super-resolution with sparse prior,, in Proc. IEEE Int. Conf. Comput. Vis., Dec. 2015, p.370–378.

[18] W. Dong, L. Zhang, R. Lukac, G. Shi, Sparse representation based image interpolation with nonlocal autoregressive modeling, IEEE Trans. Image Process. 22 (4) (2013) 1382–1394.

DOI: 10.1109/tip.2012.2231086