Towards Autonomy in Active Contour Models

Marie-Odile Berger (1) , Roger Mohr (2, 3)

1 CRIN - Centre de Recherche en Informatique de Nancy
2 MOVI - Modeling, localization, recognition and interpretation in computer vision
3 LIFIA - Laboratoire d'Informatique Fondamentale et d'Intelligence Artificielle

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.

Mots clés: convergence; pattern recognition; picture processing

Domaines: Vision par ordinateur et reconnaissance de formes [cs.CV]

Marie-Odile Berger, Roger Mohr. Towards Autonomy in Active Contour Models. International Conference on Pattern Recognition (ICPR '90), Jun 1990, Atlantic City, United States. pp.847--851, ⟨10.1109/ICPR.1990.118228⟩. ⟨inria-00548463⟩