• DocumentCode
    442664
  • Title

    Recovering facial shape using a statistical surface normal model

  • Author

    Smith, W.A.P. ; Hancock, E.R.

  • Author_Institution
    Dept. of Comput. Sci., York Univ., UK
  • Volume
    2
  • fYear
    2005
  • fDate
    11-14 Sept. 2005
  • Abstract
    This paper describes how facial shape can be modelled using a statistical model that captures variations in surface normal direction. We fit the model to intensity data using constraints on the surface normal direction provided by Lambert´s law. We demonstrate that this process yields improved facial shape recovery and allows realistic synthesis of views under novel illumination and pose.
  • Keywords
    face recognition; iterative methods; statistical analysis; azimuthal equidistant projection; facial shape; iterative method; statistical surface normal model; Azimuth; Computer science; Deformable models; Face; Humans; Lighting; Psychology; Rendering (computer graphics); Shape; Surface fitting;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Image Processing, 2005. ICIP 2005. IEEE International Conference on
  • Print_ISBN
    0-7803-9134-9
  • Type

    conf

  • DOI
    10.1109/ICIP.2005.1530004
  • Filename
    1530004
    • Link To Document
    https://search.isc.ac/dl/search/defaultta.aspx?DTC=49&DC=442664