• DocumentCode
    595516
  • Title

    Illuminant segmentation in non-uniformly lit scenes

  • Author

    Cong Phuoc Huynh ; Robles-Kelly, Antonio

  • Author_Institution
    Nat. ICT Australia, Canberra, ACT, Australia
  • fYear
    2012
  • fDate
    11-15 Nov. 2012
  • Firstpage
    3664
  • Lastpage
    3667
  • Abstract
    In this paper, we present a method for segmenting illuminants in non-uniformly lit scenes. Here, we view the illuminant colour at an image location as a mixture of the segmented illuminants. Based on the dichromatic structure of the image radiance space, we perform soft-clustering on the set of dichromatic planes corresponding to the neighbourhoods of pixel-sites in the image. We solve the soft-clustering problem with a deterministic annealing approach where the cost function is formulated based on the maximum entropy principle. We show results on real-world imagery and provide comparisons to an alternative method.
  • Keywords
    image colour analysis; image segmentation; lighting; maximum entropy methods; natural scenes; optimisation; pattern clustering; cost function; deterministic annealing approach; dichromatic planes; illuminant colour; illuminant segmentation; image location; image pixels; image radiance space dichromatic structure; maximum entropy principle; nonuniformly lit scenes; soft-clustering problem; Computer vision; Cost function; Image color analysis; Image segmentation; Light sources; Lighting; Vectors;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Pattern Recognition (ICPR), 2012 21st International Conference on
  • Conference_Location
    Tsukuba
  • ISSN
    1051-4651
  • Print_ISBN
    978-1-4673-2216-4
  • Type

    conf

  • Filename
    6460959