Image Demosaicking Using Densely Connected Convolutional Neural Network
- Authors
- Park, Bumjun; Jeong, Je chang
- Issue Date
- Jul-2018
- Publisher
- Institute of Electrical and Electronics Engineers Inc.
- Keywords
- Color filter array interpolation; Convolutional neural network; Deep learning; Demosaicking
- Citation
- Proceedings - 14th International Conference on Signal Image Technology and Internet Based Systems, SITIS 2018, pp.304 - 307
- Indexed
- SCOPUS
- Journal Title
- Proceedings - 14th International Conference on Signal Image Technology and Internet Based Systems, SITIS 2018
- Start Page
- 304
- End Page
- 307
- URI
- https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/4686
- DOI
- 10.1109/SITIS.2018.00053
- ISSN
- 0000-0000
- Abstract
- In this paper, we propose image demosaicking model using densely connected convolutional neural network. Recently, deep neural networks show improved results in image processing field compared with conventional algorithms. However, they often suffer vanishing-gradient problem which makes models hard to be trained. To solve this problem, we applied densely connected convolutional neural network. More than that, our proposed network doesn't need any initial interpolation which can reduce computational complexity. Finally, we applied sub-pixel interpolation layer which can generate demosaicked output image efficiently and accurately. Experimental results show that our proposed model outperformed conventional methods.
- Files in This Item
-
Go to Link
- Appears in
Collections - 서울 공과대학 > 서울 융합전자공학부 > 1. Journal Articles
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.