• DocumentCode
    2147288
  • Title

    Lip Contour Extraction Based on Manifold

  • Author

    YaLing, Liang ; Du Minghui

  • Author_Institution
    Sch. of Electron. & Inf. Eng., South China Univ. of Technol., Guangzhou
  • fYear
    2008
  • fDate
    30-31 Dec. 2008
  • Firstpage
    229
  • Lastpage
    232
  • Abstract
    This paper presents a method to extract the outer contour of lip based on manifold without lip model. As we all know, the red exclusion and color transform methods are used widely to extract the lip for their simplicity. Lots of modified method and some clustering method are proposed too, but most of these methods are based on the distribution of color difference or correlation between lip and skin. They can only extract the raw lip area not the contour of the lip. The edge of the lip is very important for the correction of extracted features, the quality of these features determine the application related to lip, such as lip reading and speaker identification. Based on the fact that the mouth area has high edge content and the change in lip contour is bigger than in other area, this paper uses the change of color components and based it on the frame of manifold to get the edge of the lip. The experimental results show that the proposed method is more effective in extraction outer contour of lip and more robust than red exclusion.
  • Keywords
    feature extraction; image colour analysis; color transform methods; feature extraction; lip contour extraction; lip reading; red exclusion; speaker identification; Color; Data mining; Feature extraction; Histograms; Image edge detection; Information technology; Manifolds; Mouth; Speech recognition; Working environment noise; lip contour extraction; lip reading; manifold; red exclusion;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    MultiMedia and Information Technology, 2008. MMIT '08. International Conference on
  • Conference_Location
    Three Gorges
  • Print_ISBN
    978-0-7695-3556-2
  • Type

    conf

  • DOI
    10.1109/MMIT.2008.25
  • Filename
    5089101