Narrow band region approach for active contours and surfaces

Abstract

We introduce a narrow band region approach for explicit deformable models in the perspective of 2D and 3D image segmentation. Embedding a region term into the evolution process, we derive a general framework which is applied both on a 2D parametric contour and a 3D triangular mesh. Evolution of deformable models is performed by means of energy minimization using the computationally efficient greedy algorithm. The use of a region energy related to the vicinity of the evolving surface overcomes limitations of edge-based active models while remaining time effective. Experiments with segmentation quality assessment are carried out on medical data sets.