에지예측을 이용한 RL 디컨볼루션에서의 링잉 제거
DC Field | Value | Language |
---|---|---|
dc.contributor.author | 정우진 | - |
dc.contributor.author | 박진욱 | - |
dc.contributor.author | 문영식 | - |
dc.date.accessioned | 2021-06-22T23:22:35Z | - |
dc.date.available | 2021-06-22T23:22:35Z | - |
dc.date.issued | 2014-06 | - |
dc.identifier.uri | https://scholarworks.bwise.kr/erica/handle/2021.sw.erica/22812 | - |
dc.description.abstract | Richardson-lucy deconvolution, one of the popular methods for motion deblurring, tends to produce a deblurred image with ringing artifacts. In order to reduce the artifact, we propose a new method of using edge predication and weighted richardson-lucy deconvlution. The edge prediction is a process of finding an edge region and producing a weight map. The weighted richardson-lucy deconvolution is a modified richardson-lucy deconvolution algorithm that removes the error only in the weighted region. Experimental results have shown that the proposed method produces better deblurred images with less artifacts. | - |
dc.format.extent | 3 | - |
dc.language | 한국어 | - |
dc.language.iso | KOR | - |
dc.publisher | 대한전자공학회 | - |
dc.title | 에지예측을 이용한 RL 디컨볼루션에서의 링잉 제거 | - |
dc.title.alternative | Removing Ringing Artifacts of RL Deconvolution Using Edge Estimation | - |
dc.type | Article | - |
dc.publisher.location | 대한민국 | - |
dc.identifier.bibliographicCitation | 2014년도 대한전자공학회 하계학술대회 논문집, v.37, no.1, pp 789 - 791 | - |
dc.citation.title | 2014년도 대한전자공학회 하계학술대회 논문집 | - |
dc.citation.volume | 37 | - |
dc.citation.number | 1 | - |
dc.citation.startPage | 789 | - |
dc.citation.endPage | 791 | - |
dc.description.isOpenAccess | N | - |
dc.description.journalRegisteredClass | other | - |
dc.identifier.url | https://www.dbpia.co.kr/journal/articleDetail?nodeId=NODE02438674 | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
55 Hanyangdeahak-ro, Sangnok-gu, Ansan, Gyeonggi-do, 15588, Korea+82-31-400-4269 sweetbrain@hanyang.ac.kr
COPYRIGHT © 2021 HANYANG UNIVERSITY. ALL RIGHTS RESERVED.
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.