• DocumentCode
    706202
  • Title

    A probabilistic shading invariant color distance measure

  • Author

    Wesolkowski, Slawo ; Fieguth, Paul

  • Author_Institution
    DRDC, Ottawa, ON, Canada
  • fYear
    2007
  • fDate
    3-7 Sept. 2007
  • Firstpage
    1907
  • Lastpage
    1911
  • Abstract
    We develop a probabilistic color distance measure based on hypothesis testing in order to achieve shading invariance in image segmentation. We derive this new color distance measure based on the Dichromatic Reflection Model and noise statistics. We show preliminary results of using the new semi-metric in a color image segmentation task to show its effectiveness.
  • Keywords
    image colour analysis; image segmentation; probability; Dichromatic reflection model; color image segmentation task; hypothesis testing; noise statistics; probabilistic shading invariant color distance measure; Color; Colored noise; Euclidean distance; Image color analysis; Image segmentation; Probabilistic logic;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Signal Processing Conference, 2007 15th European
  • Conference_Location
    Poznan
  • Print_ISBN
    978-839-2134-04-6
  • Type

    conf

  • Filename
    7099139