603 articles – 409 Notices  [english version]
HAL : hal-00267007, version 1

Fiche détaillée  Récupérer au format
A mixed model of active geodesic contours with gradient vector flows for X-ray microtomography segmentation
Laurence Guillot 1, Emmanuel Le Trong 2, Olivier Rozenbaum 2, Maïtine Bergounioux 1, Jean-Louis Rouet 2
(06/2009)

The structural characterization of weathered building stones of historical monuments can be achieved with a powerfull imagering technique, X-ray microtomography. It requires however a carefull extraction of each phase constituting the sample from the raw gray-level images obtained (the segmentation process). This contribution presents an original method of segmentation of such images that combines active contour models driven by gradient vector flows with a morphological preprocessing, alternate sequential filters. Preliminary results on high resolution, structuraly complex images are presented and compared to more classical approaches.
1 :  Mathématiques - Analyse, Probabilités, Modélisation - Orléans (MAPMO)
Université d'Orléans – CNRS : UMR7349
2 :  Institut des Sciences de la Terre d'Orléans (ISTO)
Université d'Orléans – CNRS : UMR6113 – Université François Rabelais - Tours – INSU
Informatique/Traitement des images
Segmentation – Alternate Sequential Filtering (ASF) – microtomography – active contours
Liste des fichiers attachés à ce document : 
PDF
GLRBR.pdf(7.4 MB)