• DocumentCode
    2037125
  • Title

    Recovering Intrinsic Images using an Illumination Invariant Image

  • Author

    Farenzena, M. ; Fusiello, A.

  • Author_Institution
    Univ. di Verona, Verona
  • Volume
    3
  • fYear
    2007
  • fDate
    Sept. 16 2007-Oct. 19 2007
  • Abstract
    In this paper a method for the extraction of shading and reflectance intrinsic images from a single uncalibrated image is presented. It is based on the classification of the image derivatives as either caused by shading or reflectance effects, using an illumination-invariant image to guide this classification. Our approach avoids the learning process -which requires ground truth intrinsic images -and obtain results comparable with the state of the art.
  • Keywords
    feature extraction; image classification; illumination invariant image; image classification; reflectance intrinsic image; shading intrinsic image; uncalibrated image; Context modeling; Filtering; Frequency; Layout; Lighting; Markov random fields; Reflectivity; Rendering (computer graphics); Shape; Testing; Intrinsic Images; Reflectance Recovery;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Image Processing, 2007. ICIP 2007. IEEE International Conference on
  • Conference_Location
    San Antonio, TX
  • ISSN
    1522-4880
  • Print_ISBN
    978-1-4244-1437-6
  • Electronic_ISBN
    1522-4880
  • Type

    conf

  • DOI
    10.1109/ICIP.2007.4379352
  • Filename
    4379352