Deep Learning Algorithms for Single Image Super-Resolution: A Systematic Review
Image super-resolution has become an important technology recently, especially in the medical and industrial fields. As such, much effort has been given to develop image super-resolution algorithms. A recent method used was convolutional neural network (CNN) based algorithms. super-resolution convol...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-04-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/10/7/867 |
| _version_ | 1797538682598588416 |
|---|---|
| author | Yoong Khang Ooi Haidi Ibrahim |
| author_facet | Yoong Khang Ooi Haidi Ibrahim |
| author_sort | Yoong Khang Ooi |
| collection | DOAJ |
| description | Image super-resolution has become an important technology recently, especially in the medical and industrial fields. As such, much effort has been given to develop image super-resolution algorithms. A recent method used was convolutional neural network (CNN) based algorithms. super-resolution convolutional neural network (SRCNN) was the pioneer of CNN-based algorithms, and it continued being improved till today through different techniques. The techniques included the type of loss functions used, upsampling module deployed, and the adopted network design strategies. In this paper, a total of 18 articles were selected through the PRISMA standard. A total of 19 algorithms were found in the selected articles and were reviewed. A few aspects are reviewed and compared, including datasets used, loss functions used, evaluation metrics applied, upsampling module deployed, and adopted design techniques. For each upsampling module and design techniques, their respective advantages and disadvantages were also summarized. |
| first_indexed | 2024-03-10T12:34:55Z |
| format | Article |
| id | doaj.art-7ec759902bc84325964c0ef7d29441ed |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-10T12:34:55Z |
| publishDate | 2021-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-7ec759902bc84325964c0ef7d29441ed2023-11-21T14:20:22ZengMDPI AGElectronics2079-92922021-04-0110786710.3390/electronics10070867Deep Learning Algorithms for Single Image Super-Resolution: A Systematic ReviewYoong Khang Ooi0Haidi Ibrahim1School of Electrical & Electronic Engineering, Engineering Campus, Universiti Sains Malaysia, Nibong Tebal 14300, Pulau Pinang, MalaysiaSchool of Electrical & Electronic Engineering, Engineering Campus, Universiti Sains Malaysia, Nibong Tebal 14300, Pulau Pinang, MalaysiaImage super-resolution has become an important technology recently, especially in the medical and industrial fields. As such, much effort has been given to develop image super-resolution algorithms. A recent method used was convolutional neural network (CNN) based algorithms. super-resolution convolutional neural network (SRCNN) was the pioneer of CNN-based algorithms, and it continued being improved till today through different techniques. The techniques included the type of loss functions used, upsampling module deployed, and the adopted network design strategies. In this paper, a total of 18 articles were selected through the PRISMA standard. A total of 19 algorithms were found in the selected articles and were reviewed. A few aspects are reviewed and compared, including datasets used, loss functions used, evaluation metrics applied, upsampling module deployed, and adopted design techniques. For each upsampling module and design techniques, their respective advantages and disadvantages were also summarized.https://www.mdpi.com/2079-9292/10/7/867deep learningsingle imagesuper-resolutionsystematic review |
| spellingShingle | Yoong Khang Ooi Haidi Ibrahim Deep Learning Algorithms for Single Image Super-Resolution: A Systematic Review Electronics deep learning single image super-resolution systematic review |
| title | Deep Learning Algorithms for Single Image Super-Resolution: A Systematic Review |
| title_full | Deep Learning Algorithms for Single Image Super-Resolution: A Systematic Review |
| title_fullStr | Deep Learning Algorithms for Single Image Super-Resolution: A Systematic Review |
| title_full_unstemmed | Deep Learning Algorithms for Single Image Super-Resolution: A Systematic Review |
| title_short | Deep Learning Algorithms for Single Image Super-Resolution: A Systematic Review |
| title_sort | deep learning algorithms for single image super resolution a systematic review |
| topic | deep learning single image super-resolution systematic review |
| url | https://www.mdpi.com/2079-9292/10/7/867 |
| work_keys_str_mv | AT yoongkhangooi deeplearningalgorithmsforsingleimagesuperresolutionasystematicreview AT haidiibrahim deeplearningalgorithmsforsingleimagesuperresolutionasystematicreview |