Image Demosaicking Using Densely Connected Convolutional Neural Network
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Park, Bumjun | - |
dc.contributor.author | Jeong, Je chang | - |
dc.date.accessioned | 2021-07-30T05:24:36Z | - |
dc.date.available | 2021-07-30T05:24:36Z | - |
dc.date.created | 2021-05-13 | - |
dc.date.issued | 2018-07 | - |
dc.identifier.issn | 0000-0000 | - |
dc.identifier.uri | https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/4686 | - |
dc.description.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. | - |
dc.language | 영어 | - |
dc.language.iso | en | - |
dc.publisher | Institute of Electrical and Electronics Engineers Inc. | - |
dc.title | Image Demosaicking Using Densely Connected Convolutional Neural Network | - |
dc.type | Article | - |
dc.contributor.affiliatedAuthor | Jeong, Je chang | - |
dc.identifier.doi | 10.1109/SITIS.2018.00053 | - |
dc.identifier.scopusid | 2-s2.0-85065910610 | - |
dc.identifier.bibliographicCitation | Proceedings - 14th International Conference on Signal Image Technology and Internet Based Systems, SITIS 2018, pp.304 - 307 | - |
dc.relation.isPartOf | Proceedings - 14th International Conference on Signal Image Technology and Internet Based Systems, SITIS 2018 | - |
dc.citation.title | Proceedings - 14th International Conference on Signal Image Technology and Internet Based Systems, SITIS 2018 | - |
dc.citation.startPage | 304 | - |
dc.citation.endPage | 307 | - |
dc.type.rims | ART | - |
dc.type.docType | Conference Paper | - |
dc.description.journalClass | 1 | - |
dc.description.isOpenAccess | N | - |
dc.description.journalRegisteredClass | scopus | - |
dc.subject.keywordPlus | Convolution | - |
dc.subject.keywordPlus | Deep learning | - |
dc.subject.keywordPlus | Image enhancement | - |
dc.subject.keywordPlus | Interpolation | - |
dc.subject.keywordPlus | Neural networks | - |
dc.subject.keywordPlus | Color filter array interpolation | - |
dc.subject.keywordPlus | Conventional algorithms | - |
dc.subject.keywordPlus | Conventional methods | - |
dc.subject.keywordPlus | Convolutional neural network | - |
dc.subject.keywordPlus | Demosaicking | - |
dc.subject.keywordPlus | Subpixel interpolation | - |
dc.subject.keywordPlus | Vanishing gradient | - |
dc.subject.keywordPlus | Deep neural networks | - |
dc.subject.keywordAuthor | Color filter array interpolation | - |
dc.subject.keywordAuthor | Convolutional neural network | - |
dc.subject.keywordAuthor | Deep learning | - |
dc.subject.keywordAuthor | Demosaicking | - |
dc.identifier.url | https://ieeexplore.ieee.org/document/8706218 | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
222, Wangsimni-ro, Seongdong-gu, Seoul, 04763, Korea+82-2-2220-1365
COPYRIGHT © 2021 HANYANG UNIVERSITY.
Certain data included herein are derived from the © Web of Science of Clarivate Analytics. All rights reserved.
You may not copy or re-distribute this material in whole or in part without the prior written consent of Clarivate Analytics.