National Tsing Hua University Institutional Repository:Face hallucination using Bayesian global estimation and local basis selection
English  |  正體中文  |  简体中文  |  全文笔数/总笔数 : 54367/62174 (87%)
造访人次 : 14149349      在线人数 : 33
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  >  Face hallucination using Bayesian global estimation and local basis selection


    题名: Face hallucination using Bayesian global estimation and local basis selection
    作者: Chih-Chung Hsu;Chia-Wen Lin;Chiou-Ting Hsu;Hong-Yuan Mark Liao
    教師: 林嘉文
    日期: 2010
    出版者: Institute of Electrical and Electronics Engineers
    關聯: Proc. IEEE Workshop Multimedia Signal Processing (MMSP), Saint-Malo, France, 4-6 Oct. 2010
    关键词: Face hallucination
    Bayesian global estimation
    local basis selection
    摘要: This paper proposes a two-step prototype-face-based scheme of hallucinating the high-resolution detail of a low-resolution input face image. The proposed scheme is mainly composed of two steps: the global estimation step and the local facial-parts refinement step. In the global estimation step, the initial high-resolution face image is hallucinated via a linear combination of the global prototype faces with a coefficient vector. Instead of estimating coefficient vector in the high-dimensional raw image domain, we propose a maximum a posteriori (MAP) estimator to estimate the optimum set of coefficients in the low-dimensional coefficient domain. In the local refinement step, the facial parts (i.e., eyes, nose and mouth) are further refined using a basis selection method based on overcomplete nonnegative matrix factorization (ONMF). Experimental results demonstrate that the proposed method can achieve significant subjective and objective improvement over state-of-the-art face hallucination methods, especially when an input face does not belong to a person in the training data set.
    相関连結: http:/
    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


    档案 描述 大小格式浏览次数


    SFX Query


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