Super-Resolution Image Restoration Using Convolutional Neural Network


  • O. Yu. Nedzelskyi National Technical University of Ukraine "Igor Sikorsky Kyiv Polytechnic Institute", Kyiv, Ukraine
  • N. О. Lashchevska National Technical University of Ukraine "Igor Sikorsky Kyiv Polytechnic Institute", Kyiv, Ukraine



super resolution, convolutional neural networks, signal-to-noise ratio, MSE loss, VGG loss, sampling reduction factor, encoder, decoder, desubpixel


The main goal of the super resolution method is to create a higher resolution image from a lower resolution image. High-resolution images provide a high pixel density, hence more detail in the original image. The need for high resolution is widespread in computer vision techniques, pattern recognition applications, or general image analysis. However, high-resolution images are not always available. This is due to the fact that the conversion processes and processing methods require ultra-powerful processes, and the equipment for obtaining high-resolution images is expensive. These problems can be overcome by using image processing algorithms that are relatively inexpensive, which has led to the concept of super-resolution. This has the advantage that it can cost less and existing low-resolution imaging systems are readily available. High resolution is essential in medical imaging for diagnosis. Many applications require zooming into a specific image area, where high resolution becomes essential, such as surveillance, forensics, and satellite imaging. The method is presented in this paper, using a convolutional neural network to reproduce super-resolution images, directly performs the conversion from a low-resolution image to an image similar to the original. To speed up the output time, the proposed method performs most computational operations in low-resolution space, while reducing the sampling does not lead to information loss. The main task of the neural network is to reconstruct the distorted image and find the ideal reconstruction function, according to which, in fact, a neural network of a simple structure creates high-quality images with better performance, such as resolution, signal-to-noise ratio, with less time spent on image restoration. During the experiment, we determined an algorithm by which the proposed neural network can reconstruct any image with different types of distortion. The super-resolution method is implemented using the python 3.6 programming language and the tensorflow and tensorlayer software modules for convolutional neural networks. Graphical data of signal-to-noise ratio, structural similarity, and loss plots are obtained using the tensorboardX module.



Yang J. and Huang T. (2017). Image Super-Resolution: Historical Overview and Future Challenges. in Super-Resolution Imaging, CRC Press, pp. 1–34. doi: 10.1201/9781439819319-1.

Kim P. (2017). Convolutional Neural Network. in MATLAB Deep Learning, Berkeley, CA: Apress, pp. 121–147. doi: 10.1007/978-1-4842-2845-6.

Li Z., Liu F., Yang W., Peng S., and Zhou J. (2022). A Survey of Convolutional Neural Networks: Analysis, Applications, and Prospects. IEEE Trans Neural Netw Learn Syst, Vol. 33, No. 12, pp. 6999–7019. doi: 10.1109/TNNLS.2021.3084827.

Albawi S., Mohammed T. A., and Al-Zawi S. (2017). Understanding of a convolutional neural network. 2017 International Conference on Engineering and Technology (ICET), pp. 1–6. doi: 10.1109/ICEngTechnol.2017.8308186.

Zhao N., Wei Q., Basarab A., Dobigeon N., Kouame D., and Tourneret J.-Y. (2016). Fast Single Image Super-Resolution Using a New Analytical Solution l2-l2 Problems. IEEE Transactions on Image Processing, Vol. 25, No. 8, pp. 3683–3697. doi: 10.1109/TIP.2016.2567075.

Ignatov A. et al. (2018). PIRM Challenge on Perceptual Image Enhancement on Smartphones: Report. Cornell University. doi: 10.48550/arXiv.1810.01641.

Fattal R. (2007). Image upsampling via imposed edge statistics. ACM SIGGRAPH 2007 papers, p. 95. doi: 10.1145/1275808.1276496.

Zhang Y., Zhao D., Zhang J., Xiong R. and Gao W. (2011). Interpolation-Dependent Image Downsampling. IEEE Transactions on Image Processing, Vol. 20, No. 11, pp. 3291–3296. doi: 10.1109/TIP.2011.2158226.

Bayar B. and Stamm M. C. (2016). A Deep Learning Approach to Universal Image Manipulation Detection Using a New Convolutional Layer. Proceedings of the 4th ACM Workshop on Information Hiding and Multimedia Security, pp. 5–10. doi: 10.1145/2909827.2930786.

Ide H. and Kurita T. (2017). Improvement of learning for CNN with ReLU activation by sparse regularization. 2017 International Joint Conference on Neural Networks (IJCNN), pp. 2684–2691. doi: 10.1109/IJCNN.2017.7966185.

Ngernplubpla J. and Chitsobhuk O. (2019). Neuro-fuzzy profile clustering in image enhancement. 2019 7th International Electrical Engineering Congress (iEECON), pp. 1–4. doi: 10.1109/iEECON45304.2019.8938965.

Govil, R. (2000). Neural Networks in Signal Processing. In: Ruan, D. (eds) Fuzzy Systems and Soft Computing in Nuclear Engineering. Studies in Fuzziness and Soft Computing, Vol 38. doi: 10.1007/978-3-7908-1866-6_11.

Shi W. et al. (2016). Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1874–1883. doi: 10.1109/CVPR.2016.207.

Ignatov A., Kobyshev N., Timofte R., and Vanhoey K. (2017). DSLR-Quality Photos on Mobile Devices with Deep Convolutional Networks. 2017 IEEE International Conference on Computer Vision (ICCV), pp. 3297–3305. doi: 10.1109/ICCV.2017.355.



How to Cite

Недзельський, . О. Ю. and Лащевська, Н. О. (2023) “Super-Resolution Image Restoration Using Convolutional Neural Network”, Visnyk NTUU KPI Seriia - Radiotekhnika Radioaparatobuduvannia, (91), pp. 79-86. doi: 10.20535/RADAP.2023.91.79-86.



Computing methods in radio electronics