Illumination Correction from Psoriasis Image Data

  • Gabriela Maletti
  • Bjarne Ersbøll
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2749)


An approach to automatically correct illumination problems in dermatological images is presented. The illumination function is estimated after combining the thematic map indicating skin -produced by an automated classification scheme- with the dermatological image data. The user is only required to specify which class has the most suitable thematic map to use in the illumination correction. Results are shown for real examples. It is also shown that the classification output improves after illumination correction.


Original Image Normal Skin Discrimination Function Circular Window Illumination Model 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


  1. 1.
    Videometer. Scholar
  2. 2.
    K. Conradsen. En Introduktion til Statistik. Bind 2. IMSOR DTH., Lyngby, 1984.Google Scholar
  3. 3.
    J. Lira. Introducción al Tratamiento Digital de Imágenes. Instituto Politécnico Nacional, Universidad Nacional Autónoma de México, Fondo de Cultura Económica., México D.F., 1 edition, September 2002.Google Scholar
  4. 4.
    G. Maletti and B. Ersbøll. A combined alignment and registration scheme of psoriasis lesions images. International Journal in Information Sciences, 2003. Accepted.Google Scholar
  5. 5.
    G. Maletti and B. Ersbøll. A hierarchical classification scheme of psoriasis images. Technical Report 6, Department of Informatics and Mathematical Modelling. Technical University of Denmark., Kgs. Lyngby. Denmark., March 2003.Google Scholar
  6. 6.
    G. Maletti, B. Ersbøll, and K. Conradsen. A contextual classifier that only requires one prototype pixel for each class. IEEE Transactions on Nuclear Science, 49(3):700–706, June 2002.CrossRefGoogle Scholar
  7. 7.
    U. Mattsson, A Jönsson, M. Jontell, and J. Cassuto. Digital image analysis (dia) of color changes in human skin exposed to standardized thermal injury and comparison with laser doppler measurements. Computer Methods and Programs in Biomedicine, 50:31–42, 1996.CrossRefGoogle Scholar
  8. 8.
    M. Soriano, B. Martinkauppi, S. Huovinen, and M. Laaksonen. Skin detection in video under changing illumination conditions. 15th International Conference on Pattern Recognition, 1:839–842, 2000.Google Scholar
  9. 9.
    Y. Wang and T. Adali. Signal Processing for Magnetic Resonance Imaging and Spectroscopy. Stocastic Model Based Image Analysis, chapter 14, pages 1–34. 2000. (Topics in Biomedical Imaging Course Notes.).Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2003

Authors and Affiliations

  • Gabriela Maletti
    • 1
  • Bjarne Ersbøll
    • 1
  1. 1.Department of Informatics and Mathematical ModellingTechnical University of DenmarkKgs. LyngbyDenmark

Personalised recommendations