Implicit active contour models are widely used in image processing and computer vision tasks. Most implementations, however, are based on explicit updating schemes and are therefore of limited computational efficiency. In this paper, we present fast algorithms based on the semi-implicit additive operator splitting (AOS) scheme for both the geometric and the geodesic active contour model. Our experimental results with synthetic and real-world images demonstrate that AOS-based implementations clearly outperform their explicit counterparts.
Dieser Eintrag ist Teil der Universitätsbibliographie.
Search Authors in