3531 articles – 5253 Notices  [english version]

inria-00187232, version 1

Segmentation using vector-attribute filters: methodology and application to dermatological imaging

Benoît Naegel () 1, Nicolas Passat a, 2, Nicolas Boch 3, Michel Kocher 4

8th International Symposium on Mathematical Morphology - ISMM 2007 (2007)

Résumé : Attribute-based filters can be involved in analysis and processing of images by considering attributes of various kinds (quantitative, qualitative, structural). Despite their potential usefulness, they are quite infrequently considered in the development of real applications. A cause of this underuse is probably the difficulty to determine correct parameters for non-scalar attributes in a fast and efficient fashion. This paper proposes a general definition of vector-attribute filters for grey-level images and describes some solutions to perform detection tasks using vector-attributes and parameters determined from a learning set. Based on these elements, an interactive segmentation method for dermatological application has been developed.

  • a –  Université Louis Pasteur - Strasbourg I
  • 1 :  QGAR (INRIA Lorraine - LORIA)
  • INRIA – Université Henri Poincaré - Nancy I – Université Nancy II – Institut National Polytechnique de Lorraine (INPL) – CNRS : UMR7503
  • 2 :  Laboratoire des Sciences de l'Image, de l'Informatique et de la Télédétection (LSIIT)
  • CNRS : UMR7005 – Université Louis Pasteur - Strasbourg I
  • 3 :  Digital Imaging Unit
  • Geneva University Hospital
  • 4 :  EIG
  • HES
  • Domaine : Informatique/Imagerie médicale
    Informatique/Traitement des images
  • Mots-clés : vector-attribute filters – component-trees – segmentation – dermatological imaging
 
  • inria-00187232, version 1
  • http://hal.inria.fr/inria-00187232
  • oai:hal.inria.fr:inria-00187232
  • Contributeur : Benoît Naegel <>
  • Soumis le : Mercredi 14 Novembre 2007, 09:00:27
  • Dernière modification le : Lundi 3 Décembre 2007, 17:41:44