• DocumentCode
    2145096
  • Title

    3-D Face Reconstruction Using RBF and B Spline Method

  • Author

    He, Guo-hui ; Zhu, Bin ; Gan, Jun-Ying

  • Author_Institution
    Sch. of Inf., Wuyi Univ., Jiangmen
  • Volume
    1
  • fYear
    2008
  • fDate
    27-30 May 2008
  • Firstpage
    239
  • Lastpage
    243
  • Abstract
    3-D specific face model construction by way of 2-D face image is an active topic in 3-D face modeling research. In this paper, stereoscopic sense of vision is used to reconstruct 3-D feature points. Then multi-layer and multi-region RBF (radial basis function) based on feature points of frontal and profile face image is adopted for reconstructing the generic face model to get 3-D specific face model with visible organ characters. Moreover, B spline is used in 3-D face curve reconstruction. Then the near face global texture is mapped onto the reconstructed specific face model and the 3-D realistic specific human face model is obtained. Experiments show that the method is easy for constructing near face global texture, in which the reconstructed specific face model is natural and realistic, and can be used for realistic specific face modeling in facial animation.
  • Keywords
    computer animation; face recognition; image reconstruction; image texture; radial basis function networks; splines (mathematics); stereo image processing; 3-D face curve reconstruction; B spline method; RBF; face global texture mapping; facial animation; radial basis function; stereoscopic vision; Face detection; Facial animation; Humans; Image reconstruction; Layout; Rendering (computer graphics); Shape; Signal processing algorithms; Spline; Toy industry; B spline; RBFs; face reconstruction; feature extraction; stereoscopic sense of vision;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Image and Signal Processing, 2008. CISP '08. Congress on
  • Conference_Location
    Sanya, Hainan
  • Print_ISBN
    978-0-7695-3119-9
  • Type

    conf

  • DOI
    10.1109/CISP.2008.70
  • Filename
    4566155