Single Image Super Resolution Reconstruction Based on Recursive Residual Convolutional Neural Network
- Title
- Single Image Super Resolution Reconstruction Based on Recursive Residual Convolutional Neural Network
- Author
- 정제창
- Issue Date
- 2019-06
- Publisher
- 한국방송∙미디어공학회
- Citation
- 한국방송·미디어공학회 2019 하계학술대회, Page. 98-101
- Abstract
- At present, deep convolutional neural networks have made a very important contribution in single-image super-resolution. Through the learning of the neural networks, the features of input images are transformed and combined to establish a nonlinear mapping of low-resolution images to high-resolution images. Some previous methods are difficult to train and take up a lot of memory. In this paper, we proposed a simple and compact deep recursive residual network learning the features for single image super resolution. Global residual learning and local residual learning are used to reduce the problems of training deep neural networks. And the recursive structure controls the number of parameters to save memory. Experimental results show that the proposed method improved image qualities that occur in previous methods.
- URI
- http://www.dbpia.co.kr/view/ar_view.asp?arid=4801356https://repository.hanyang.ac.kr/handle/20.500.11754/151460
- Appears in Collections:
- COLLEGE OF ENGINEERING[S](공과대학) > ELECTRONIC ENGINEERING(융합전자공학부) > Articles
- Files in This Item:
There are no files associated with this item.
- Export
- RIS (EndNote)
- XLS (Excel)
- XML