• DocumentCode
    167853
  • Title

    Interactive Tongue Body Segmentation

  • Author

    Zhenchao Cui ; Hongzhi Zhang ; Wangmeng Zuo

  • Author_Institution
    Sch. of Comput. Sci. & Technol., Harbin Inst. of Technol., Harbin, China
  • fYear
    2014
  • fDate
    May 30 2014-June 1 2014
  • Firstpage
    26
  • Lastpage
    31
  • Abstract
    Despite the progress in tongue body segmentation, it remains a challenge to correctly segment the tongue body from any tongue images. As one possible solution, conventional interactive segmentation methods usually are not tailored for tongue body segmentation, and suffer from several limitations like poor efficiency and less specificity. In this paper, we extend the GaborFM method, and propose an interactive tongue body segmentation (ITBS) method by considering three principles: convergence, efficiency, and ease of use. Using the segmentation result of GaborFM for initialization, the proposed method allows the user to modify the segmentation by simply drawing a line segment at the true tongue body contour. Then ITBS exploits the information provided by the user to update the masks and edges, and update contour using fast marching. Experimental results show that ITBS can obtain correct results after less than 0.5 times of interactions in average, and is much efficient than conventional interactive segmentation methods.
  • Keywords
    biological organs; image segmentation; medical image processing; GaborFM method; conventional interactive segmentation methods; convergence; interactive tongue body segmentation; line segment drawing; tongue images; true tongue body contour; Educational institutions; Guidelines; Image edge detection; Image segmentation; Materials; Reliability; Tongue; GaborFM; Tongue diagnosis; interactive tongue body segmentation;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Medical Biometrics, 2014 International Conference on
  • Conference_Location
    Shenzhen
  • Print_ISBN
    978-1-4799-4014-1
  • Type

    conf

  • DOI
    10.1109/ICMB.2014.12
  • Filename
    6845820