IMAGES SEGMENTATION BY USING B-SPLINE ACTIVE CONTOURS (B-SNAKE) ONTHE CHAN-VESE MODE

Type : Article de conférence
Auteur(s) :  Y. Boutiche, A. Bessekri
Année :  2010
Domaine : Electronique
Conférence: The 2nd International Conference on welding, nondestructive testing and the industry of materials and alloys (ICWNDT-MI’10)
Lieu de la conférence:  Oran, Algeria
Résumé en PDF :  (résumé en pdf)
Fulltext en PDF :  (.pdf)
Mots clés :  Edge detection, Active contour, Chanend Vese functional, B-spline

Résumé : 

In this work, we propose an active contour model based on the Chan-Vese functional. The total energy to be minimised is described essentially by the averages intensities inside and outside the curve. This model can detect object whose boundaries are not defined by gradient, it's a matter of the active contour model biased regions. For increasing the performance of segmentation, we are introducing the B-spline function to describe the active contour. The experiments reported in the paper, performed on synthetic noise images confirm the adequacy and good performance of the approach. We close this paper with a conclusion