• DocumentCode
    3243259
  • Title

    Analysis of the Watershed Algorithms Based on the Breadth-First and Depth-First Exploring Methods

  • Author

    Korbes, A. ; de Alencar Lotufo, Roberto

  • Author_Institution
    Dept. of Comput. Eng. & Ind. Autom. - DCA, Univ. of Campinas - UNICAMP, Campinas, Brazil
  • fYear
    2009
  • fDate
    11-15 Oct. 2009
  • Firstpage
    133
  • Lastpage
    140
  • Abstract
    In this paper, fifteen watershed algorithms are reviewed. For clarity, first we expose two graph exploring methods modified to be guidelines for understanding the approaches taken by these algorithms: the breadth-first watershed and the depth-first watershed. Both paradigms rely on the visiting order applied by the algorithms. The breadth-first is more recognizable as a seed region growing or marker expansion process, grouping both methods based on flooding and hierarchical queue. The depth-first groups the algorithms based on the drop of water simulation, forming a simple path until a regional minimum is found. We analyze and classify fifteen algorithms, and two of them were better characterized. Along with this, some useful information (i.e. use of markers and line over pixel) is organized, in order to facilitate the choice of an algorithm.
  • Keywords
    graph theory; image segmentation; tree searching; breadth-first exploring methods; depth-first exploring methods; flooding queue; graph exploring methods; hierarchical queue; marker expansion process; seed region growing process; water simulation; watershed algorithms; Algorithm design and analysis; Automation; Computer graphics; Computer industry; Floods; Guidelines; Image analysis; Image processing; Image segmentation; Proposals; image segmentation; watershed algorithms; watershed transform;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Computer Graphics and Image Processing (SIBGRAPI), 2009 XXII Brazilian Symposium on
  • Conference_Location
    Rio de Janiero
  • ISSN
    1550-1834
  • Print_ISBN
    978-1-4244-4978-1
  • Electronic_ISBN
    1550-1834
  • Type

    conf

  • DOI
    10.1109/SIBGRAPI.2009.43
  • Filename
    5395230