National Tsing Hua University Institutional Repository:Self-learning-based single image super-resolution of a highly compressed image
English  |  正體中文  |  简体中文  |  全文笔数/总笔数 : 54367/62174 (87%)
造访人次 : 13672184      在线人数 : 18
RC Version 6.0 © Powered By DSPACE, MIT. Enhanced by NTHU Library IR team.
搜寻范围 查询小技巧:
  • 您可在西文检索词汇前后加上"双引号",以获取较精准的检索结果
  • 若欲以作者姓名搜寻,建议至进阶搜寻限定作者字段,可获得较完整数据
  • 进阶搜寻
    National Tsing Hua University Institutional Repository > 電機資訊學院 > 電機工程學系 > 會議論文  >  Self-learning-based single image super-resolution of a highly compressed image


    jsp.display-item.identifier=請使用永久網址來引用或連結此文件: http://nthur.lib.nthu.edu.tw/dspace/handle/987654321/84014


    题名: Self-learning-based single image super-resolution of a highly compressed image
    作者: Li-Wei Kang;Bo-Chi Chuang;Chih-Chung Hsu;Chia-Wen Lin;Chia-Hung Yeh
    教師: 林嘉文
    日期: 2013
    出版者: Institute of Electrical and Electronics Engineers
    關聯: IEEE 15th International Workshop on Multimedia Signal Processing (MMSP), Pula, Sept. 30 2013-Oct. 2 2013, Pages 224 - 229
    摘要: Low-quality images are usually not only with low-resolution, but also suffer from compression artifacts (blocking artifact is treated as an example in this paper). Directly performing image super-resolution (SR) to a highly compressed (low-quality) image would also simultaneously magnify the blocking artifacts, resulting in unpleasing visual quality. In this paper, we propose a self-learning-based SR framework to simultaneously achieve single-image SR and compression artifact removal for a highly-compressed image. We argue that individually performing deblocking first, followed by SR to an image, would usually inevitably lose some image details induced by deblocking, which may be useful for SR, resulting in worse SR result. In our method, we propose to self-learn image sparse representation for modeling the relationship between low and high-resolution image patches in terms of the learned dictionaries, respectively, for image patches with and without blocking artifacts. As a result, image SR and deblocking can be simultaneously achieved via sparse representation and MCA (morphological component analysis)-based image decomposition. Experimental results demonstrate the efficacy of the proposed algorithm.
    相関连結: http://www.ieee.org/
    URI: http://nthur.lib.nthu.edu.tw/dspace/handle/987654321/84014
    显示于类别:[電機工程學系] 會議論文
    [光電研究中心] 會議論文

    文件中的档案:

    档案 描述 大小格式浏览次数
    index.html0KbHTML1534检视/开启


    在NTHUR中所有的資料項目都受到原著作權保護,僅提供學術研究及教育使用,敬請尊重著作權人之權益。若須利用於商業或營利,請先取得著作權人授權。
    若發現本網站收錄之內容有侵害著作權人權益之情事,請權利人通知本網站管理者(smluo@lib.nthu.edu.tw),管理者將立即採取移除該內容等補救措施。

    SFX Query

    與系統管理員聯絡

    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - 回馈