National Tsing Hua University Institutional Repository:Image super-resolution via feature-based affine transform
English  |  正體中文  |  简体中文  |  全文笔数/总笔数 : 54367/62174 (87%)
造访人次 : 14250782      在线人数 : 40
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  >  Image super-resolution via feature-based affine transform


    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/987654321/84003


    题名: Image super-resolution via feature-based affine transform
    作者: Chih-Chung Hsu;Chia-Wen Lin
    教師: 林嘉文
    日期: 2011
    出版者: Institute of Electrical and Electronics Engineers
    關聯: Proc. IEEE Workshop Multimedia Signal Processing (MMSP), Hang-Zhou, China, 17-19 Oct. 2011, Pages 1-5
    关键词: super-resolution
    affine transform
    摘要: State-of-the-art image super-resolution methods usually rely on search in a comprehensive dataset for appropriate high-resolution patch candidates to achieve good visual quality of reconstructed image. Exploiting different scales and orientations in images can effectively enrich a dataset. A large dataset, however, usually leads to high computational complexity and memory requirement, which makes the implementation impractical. This paper proposes a universal framework for enriching the dataset for search-based super-resolution schemes with reasonable computation and memory cost. Toward this end, the proposed method first extracts important features with multiple scales and orientations of patches based on the SIFT (Scale-invariant feature transform) descriptors and then use the extracted features to search in the dataset for the best-match HR patch(es). Once the matched features of patches are found, the found HR patch will be aligned with LR patch using homography estimation. Experimental results demonstrate that the proposed method achieves significant subjective and objective improvement when integrated with several state-of-the-art image super-resolution methods without significantly increasing the cost.
    相関连結: http:/dx.doi.org/10.1109/MMSP.2011.6093845
    http://www.ieee.org/
    URI: http://nthur.lib.nthu.edu.tw/dspace/handle/987654321/84003
    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.html0KbHTML1287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