• DocumentCode
    2266913
  • Title

    A phase field higher-order active contour model of directed networks

  • Author

    El Ghoul, Aymen ; Jermyn, Ian H. ; Zerubia, Josiane

  • Author_Institution
    ARIANA, UNSA, Sophia Antipolis, France
  • fYear
    2009
  • fDate
    Sept. 27 2009-Oct. 4 2009
  • Firstpage
    398
  • Lastpage
    404
  • Abstract
    The segmentation of directed networks is an important problem in many domains, e.g. medical imaging (vascular networks) and remote sensing (river networks). Directed networks carry a unidirectional flow in each branch, which leads to characteristic geometric properties. In this paper, we present a nonlocal phase field model of directed networks. In addition to a scalar field representing a region by its smoothed characteristic function and interacting non-locally so as to favour network configurations, the model contains a vector field representing the `flow´ through the network branches. The vector field is strongly encouraged to be zero outside, and of unit magnitude inside the region; and to have zero divergence. This prolongs network branches; controls width variation along a branch; and produces asymmetric junctions for which total incoming branch width approximately equals total outgoing branch width. In conjunction with a new interaction function, it also allows a broad range of stable branch widths. We analyse the energy to constrain the parameters, and show geometric experiments confirming the above behaviour. We also show a segmentation result on a synthetic river image.
  • Keywords
    biomedical imaging; directed graphs; image segmentation; remote sensing; directed networks segmentation; medical imaging; phase field; remote sensing; river networks; vascular networks; Active contours; Computer vision; Conferences;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Computer Vision Workshops (ICCV Workshops), 2009 IEEE 12th International Conference on
  • Conference_Location
    Kyoto
  • Print_ISBN
    978-1-4244-4442-7
  • Electronic_ISBN
    978-1-4244-4441-0
  • Type

    conf

  • DOI
    10.1109/ICCVW.2009.5457672
  • Filename
    5457672