Title :
Minimal surfaces based object segmentation
Author :
Caselles, Vincent ; Kimmel, Ron ; Sapiro, Guillermo ; Sbert, Catalina
Author_Institution :
Dept. of Math. & Inf., Univ. de les Illes Balears, Palma de Mallorca, Spain
fDate :
4/1/1997 12:00:00 AM
Abstract :
A geometric approach for 3D object segmentation and representation is presented. The segmentation is obtained by deformable surfaces moving towards the objects to be detected in the 3D image. The model is based on curvature motion and the computation of surfaces with minimal areas, better known as minimal surfaces. The space where the surfaces are computed is induced from the 3D image (volumetric data) in which the objects are to be detected. The model links between classical deformable surfaces obtained via energy minimization, and intrinsic ones derived from curvature based flows. The new approach is stable, robust, and automatically handles changes in the surface topology during the deformation
Keywords :
geometry; image segmentation; minimisation; object detection; 3D image; 3D object segmentation; classical deformable surfaces; curvature based flows; curvature motion; deformable surfaces; energy minimization; geometric approach; minimal surfaces based object segmentation; object representation; surface computation; volumetric data; Active contours; Biomedical imaging; Deformable models; Image segmentation; Motion analysis; Object detection; Object segmentation; Robustness; Solid modeling; Topology;
Journal_Title :
Pattern Analysis and Machine Intelligence, IEEE Transactions on
