HAL: hal-00267007, version 1

Detailed view

Export this paper BibTeX - EndNote - TEI - RefWorks -

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

(2009-06)

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

Subject

:

Computer Science/Image Processing

Keyword(s): Segmentation – Alternate Sequential Filtering (ASF) – microtomography – active contours

hal-00267007, version 1

http://hal.archives-ouvertes.fr/hal-00267007

oai:hal.archives-ouvertes.fr:hal-00267007

From: Maïtine Bergounioux <>

Submitted on: Wednesday, 26 March 2008 11:25:51

Updated on: Monday, 25 May 2009 19:02:12