DocumentCode
3222278
Title
Towards autonomy in active contour models
Author
Berger, Marie-Odile ; Mohr, Roger
Author_Institution
INRIA Lorraine/CRIN, Vandoeuvre, France
Volume
i
fYear
1990
fDate
16-21 Jun 1990
Firstpage
847
Abstract
The strengths and the drawbacks of active contour models are described, and the absolute necessity of a criterion for assessing the solutions is pointed out. A method called snake growing, based on successive lengthenings of the snake, is proposed. The strength of this approach is that, at each stage, good convergence conditions are realized and initialization problems can be eliminated
Keywords
convergence; pattern recognition; picture processing; active contour models; convergence; snake growing; solution assessment criterion; Active contours; Computer vision; Detectors; Elasticity; Image edge detection; Image segmentation; Minimization methods; Motion detection; Spline; Tracking;
fLanguage
English
Publisher
ieee
Conference_Titel
Pattern Recognition, 1990. Proceedings., 10th International Conference on
Conference_Location
Atlantic City, NJ
Print_ISBN
0-8186-2062-5
Type
conf
DOI
10.1109/ICPR.1990.118228
Filename
118228
Link To Document