A new B-Spline based active contour approach

Sergio Nogueira (1, 2) , Yassine Ruichek (2)

1 MAIA - Autonomous intelligent machine
2 SET - Laboratoire Systèmes et Transports

This paper proposes a new B-spline based active contour model for extracting areas of interest in an image. The model is governed by original external and internal energies. A self-adaptive technique for energies regulation is used to improve the convergence in terms of quality and rapidity. An adding control point procedure is introduced in order to improve the active contour convergence towards desired image characteristics. Real time applications like object tracking and/or detection could be considered using this new proposed active contour model.

Domaines: Vision par ordinateur et reconnaissance de formes [cs.CV]; Traitement du texte et du document

Sergio Nogueira, Yassine Ruichek. A new B-Spline based active contour approach. IAPR Conference on Machine Vision Applications - MVA 2007, May 2007, Tokyo, Japan. ⟨inria-00175743⟩