• DocumentCode
    2508716
  • Title

    Color Constancy Using Standard Deviation of Color Channels

  • Author

    Choudhury, Anustup ; Medioni, Gerard

  • Author_Institution
    Dept. of Comput. Sci., Univ. of Southern California, Los Angeles, CA, USA
  • fYear
    2010
  • fDate
    23-26 Aug. 2010
  • Firstpage
    1722
  • Lastpage
    1726
  • Abstract
    We address here the problem of color constancy and propose a new method to achieve color constancy based on the statistics of images with color cast. Images with color cast have standard deviation of one color channel significantly different from that of other color channels. This observation is also applicable to local patches of images and ratio of the maximum and minimum standard deviation of color channels of local patches is used as a prior to select a pixel color as illumination color. We provide extensive validation of our method on commonly used datasets having images under varying illumination conditions and show our method to be robust to choice of dataset and at least as good as current state-of-the-art color constancy approaches.
  • Keywords
    image colour analysis; color channels; color constancy approach; illumination color; image local patches; minimum standard deviation; pixel color; Artificial neural networks; Classification algorithms; Estimation; Histograms; Image color analysis; Lighting; Pixel; color; color constancy; illumination;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Pattern Recognition (ICPR), 2010 20th International Conference on
  • Conference_Location
    Istanbul
  • ISSN
    1051-4651
  • Print_ISBN
    978-1-4244-7542-1
  • Type

    conf

  • DOI
    10.1109/ICPR.2010.426
  • Filename
    5597476