• DocumentCode
    2552514
  • Title

    Range image segmentation: the user´s dilemma

  • Author

    Hoover, A. ; Jean-Baptiste, G. ; Xiaoyi Jiang ; Flynn, P.J. ; Bunke, H. ; Goldgof, D. ; Bowyer, K.

  • Author_Institution
    Dept. of Comput. Sci. & Eng., Univ. of South Florida, Tampa, FL, USA
  • fYear
    1995
  • fDate
    21-23 Nov. 1995
  • Firstpage
    323
  • Lastpage
    328
  • Abstract
    A methodology for evaluating range image segmentation algorithms is proposed. This methodology involves (a) a common set of images that have manually specified ground truth and (b) a set of defined performance metrics for instances of correctly segmented, missed and noise regions, over- and under-segmentation, and accuracy of the recovered geometry. A tool is used to objectively compare a machine generated segmentation against the specified ground truth. Three research groups have contributed to evaluate their own algorithm for segmenting a range image into planar patches.
  • Keywords
    image segmentation; common set of images; defined performance metrics; machine generated segmentation; manually specified ground truth; planar patches; range image segmentation; Acoustic noise; Acoustical engineering; Computer science; Computer vision; Image motion analysis; Image segmentation; Informatics; Measurement standards; Testing; Topology;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Computer Vision, 1995. Proceedings., International Symposium on
  • Conference_Location
    Coral Gables, FL, USA
  • Print_ISBN
    0-8186-7190-4
  • Type

    conf

  • DOI
    10.1109/ISCV.1995.477022
  • Filename
    477022