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  |  Items with full text/Total items : 54367/62174 (87%)
Visitors : 14149391      Online Users : 36
RC Version 6.0 © Powered By DSPACE, MIT. Enhanced by NTHU Library IR team.
Scope Tips:
  • please add "double quotation mark" for query phrases to get precise results
  • please goto advance search for comprehansive author search
  • Adv. Search
    HomeLoginUploadHelpAboutAdminister Goto mobile version
    NTHUR > College of Electrical Engineering and Computer Science > Department of Electrical Engineering > EE Conference Papers >  Face hallucination using Bayesian global estimation and local basis selection

    Please use this identifier to cite or link to this item:

    Title: Face hallucination using Bayesian global estimation and local basis selection
    Authors: Chih-Chung Hsu;Chia-Wen Lin;Chiou-Ting Hsu;Hong-Yuan Mark Liao
    Teacher: 林嘉文
    Date: 2010
    Publisher: Institute of Electrical and Electronics Engineers
    Relation: Proc. IEEE Workshop Multimedia Signal Processing (MMSP), Saint-Malo, France, 4-6 Oct. 2010
    Keywords: Face hallucination
    Bayesian global estimation
    local basis selection
    Abstract: 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.
    Relation Link: http:/
    Appears in Collections:[Department of Electrical Engineering] EE Conference Papers
    [Center for Photonles Research ] CPR Conference Papers

    Files in This Item:

    File Description SizeFormat


    SFX Query


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