Abstract
In this paper, we propose a single image super-resolution (SR) method based on frequency-dependent training of convolutional neural networks. Several researchers have focused on the reconstruction of super-resolution images by training a single convolutional neural network. In the proposed method, we divided the input images into three sub-frequency groups and then trained a convolutional neural network for each sub-frequency group. Then, the final output images were reconstructed by combining the SR images from the multiple networks. Experimental results show that the proposed training method produces promising performance.
| Original language | English |
|---|---|
| Title of host publication | Proceedings - 2020 IEEE International Conference on Industrial Technology, ICIT 2020 |
| Publisher | Institute of Electrical and Electronics Engineers Inc. |
| Pages | 692-695 |
| Number of pages | 4 |
| ISBN (Electronic) | 9781728157542 |
| DOIs | |
| Publication status | Published - 2020 Feb |
| Event | 21st IEEE International Conference on Industrial Technology, ICIT 2020 - Buenos Aires, Argentina Duration: 2020 Feb 26 → 2020 Feb 28 |
Publication series
| Name | Proceedings of the IEEE International Conference on Industrial Technology |
|---|---|
| Volume | 2020-February |
Conference
| Conference | 21st IEEE International Conference on Industrial Technology, ICIT 2020 |
|---|---|
| Country/Territory | Argentina |
| City | Buenos Aires |
| Period | 20/2/26 → 20/2/28 |
Bibliographical note
Funding Information:ACKNOWLEDGEMENT This work was supported by the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIT) (2018R1D1A1B07050345).
Publisher Copyright:
© 2020 IEEE.
All Science Journal Classification (ASJC) codes
- Computer Science Applications
- Electrical and Electronic Engineering