Optimization of Image Super-Resolution through Artificial Neural Networks and Cloud Implementation
Abstract views: 27
/ 
PDF downloads: 15
DOI:
https://doi.org/10.5281/zenodo.14957442Keywords:
Super-Resolution, Artificial Neural Networks, Model Compression, Cloud Deployment, Image UpscalingAbstract
This paper presents an optimized Super-Resolution model that enhances image upscaling
through the use of artificial neural networks and cutting-edge processing techniques. The model focuses
on reducing inference time via compression methods like quantization and pruning. Additionally, a web
application has been developed to facilitate easy interaction with users.
The study evaluates several deep learning architectures, including SRCNN, EDSR, and RRDB, using a
training set of over 4,000 images. These images are processed on an Nvidia GTX 1650 GPU to fine-tune
parameters and improve performance. The model's effectiveness is tested with upscaling factors of x2, x3,
and x4, focusing on the quality of the details recovered and the efficiency of the execution. For practical
deployment and scalability, the system is hosted on a cloud platform utilizing technologies like
TensorFlow, Keras, and Flask. The corresponding web application enables users to upload images,
choose upscaling parameters, and retrieve enhanced results within a response time of 300 milliseconds or
less.
The results demonstrate that the combination of model optimization and cloud deployment offers an
effective solution for real-time image enhancement. This approach has potential applications in photo
processing, medical visualization, and recovery of low-resolution visual data, proving its versatility and
utility in various fields.
Downloads
References
L. Yue, H. Shen, J. Li, Q. Yuan, H. Zhang, and L. Zhang, “Image super-resolution: The techniques, applications, and future,” Signal Processing, vol. 128, pp. 389–408, Nov. 2016, doi: 10.1016/j.sigpro.2016.05.002.
M. Egmont-Petersen, D. de Ridder, and H. Handels, “Image processing with neural networks—a review,” Pattern Recognit, vol. 35, no. 10, pp. 2279–2301, Oct. 2002, doi: 10.1016/S0031-3203(01)00178-9.
M. J. A. Rasool, S. Ahmad, S. Mardieva, S. Akter, and T. K. Whangbo, “A Comprehensive Survey on Real-Time Image Super-Resolution for IoT and Delay-Sensitive Applications,” Applied Sciences, vol. 15, no. 1, p. 274, Dec. 2024, doi: 10.3390/app15010274.
S.-C. Zhou, Y.-Z. Wang, H. Wen, Q.-Y. He, and Y.-H. Zou, “Balanced Quantization: An Effective and Efficient Approach to Quantized Neural Networks,” J Comput Sci Technol, vol. 32, no. 4, pp. 667–682, Jul. 2017, doi: 10.1007/s11390-017-1750-y.
S. Anwar, K. Hwang, and W. Sung, “Structured Pruning of Deep Convolutional Neural Networks,” ACM J Emerg Technol Comput Syst, vol. 13, no. 3, pp. 1–18, Jul. 2017, doi: 10.1145/3005348.
Yang, W., Zhang, X., & Sun, Y. (2019). W. Yang, X. Zhang, and Y. Sun, "Deep learning for single image super-resolution: A survey," Trends in Signal Processing, vol. 2, no. 3, pp. 123-148, 2019.
Shi, W., Caballero, J., Huszár, F., Totz, J., Aitken, A. P., Bishop, R., Rueckert, D., & Wang, Z. (2016). W. Shi, J. Caballero, F. Huszár, J. Totz, A. P. Aitken, R. Bishop, D. Rueckert, and Z. Wang, "Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network," in Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR), 2016, pp. 1874-1883.
Ledig, C., Theis, L., Huszár, F., Caballero, J., Cunningham, A., Acosta, A., Aitken, A., Tejani, A., Totz, J., Wang, Z., & Shi, B. (2017). C. Ledig, L. Theis, F. Huszár, J. Caballero, A. Cunningham, A. Acosta, A. Aitken, A. Tejani, J. Totz, Z. Wang, and B. Shi, "Photo-realistic single image super-resolution using a generative adversarial network," in Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR), 2017, pp. 4681-4690.
Timofte, R., Agustsson, E., Van Gool, L., Yang, M., & Zhang, L. (2017). R. Timofte, E. Agustsson, L. Van Gool, M. Yang, and L. Zhang, "NTIRE 2017 challenge on single image super-resolution: Methods and results," in Proc. IEEE Conf. Computer Vision and Pattern Recognition Workshops (CVPRW), 2017, pp. 114-125.
Hertzmann, A. (2018). A. Hertzmann, "Can computers create art?" Arts, vol. 7, no. 2, p. 18, 2018.
Zhang, Q., Zhao, S., & LeCun, Y. (2020). Q. Zhang, S. Zhao, and Y. LeCun, "Cloud-based deep learning solutions for AI applications," Journal of Cloud Computing, vol. 9, no. 1, p. 44, 2020.
C. Dong, C. C. Loy, K. He, and X. Tang, "Learning a deep convolutional network for image super-resolution," in Proc. European Conf. on Computer Vision (ECCV), 2014, pp. 184-199.
J. Kim, J. K. Lee, and K. M. Lee, "Accurate image super-resolution using very deep convolutional networks," in Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2016, pp. 1646-1654.
W. S. Lai, J. B. Huang, N. Ahuja, and M. H. Yang, "Deep laplacian pyramid networks for fast and accurate super-resolution," in Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2017, pp. 624-632.
X. Wang, K. Yu, S. Wu, J. Gu, Y. Liu, C. Dong, Y. Qiao, and C. Change Loy, "ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks," in Proc. European Conf. on Computer Vision Workshops (ECCVW), 2018.
Y. Zhang, K. Li, K. Li, L. Wang, B. Zhong, and Y. Fu, "Image super-resolution using very deep residual channel attention networks," in Proc. European Conf. on Computer Vision (ECCV), 2018, pp. 286-301.
A. Tewari, M. Zollhöfer, H. Kim, P. Garrido, F. Bernard, P. Perez, and C. Theobalt, "State of the art on neural rendering," Computer Graphics Forum, vol. 39, no. 2, pp. 701-727, 2020.
E. Tabaku, E. Vyshka, R. Kapçiu, A. Shehi, and E. Smajli, “UTILIZING ARTIFICIAL INTELLIGENCE IN ENERGY MANAGEMENT SYSTEMS TO IMPROVE CARBON EMISSION REDUCTION AND SUSTAINABILITY,” Jurnal Ilmiah Ilmu Terapan Universitas Jambi, vol. 9, no. 1, pp. 393–405, Feb. 2025, doi: 10.22437/jiituj.v9i1.38665.
E. Tabaku, “Artificial Intelligence in E-commerce: A Case Study of Albanian Customers,” Interdisciplinary Journal of Research and Development, vol. 11, no. 2, p. 107, Jul. 2024, doi: 10.56345/ijrdv11n214.
E. Tabaku, E. Duci, R. Kapciu, and A. M. Kosova, “Exploring the Impact of Artificial Intelligence in Banking: A Case Study on the Integration of Virtual Assistants in Customer Service,” International Research Journal of Modernization in Engineering Technology and Science, Jan. 2025, doi: 10.56726/IRJMETS66700.
E. Tabaku, “Improving High Availability Services Using KVM Full Virtualization,” European Journal of Computer Science and Information Technology, vol. 13, no. 1, pp. 1–15, Jan. 2025, doi: 10.37745/ejcsit.2013/vol13n1115.
