Physically-based active shape models: initialization and optimization

摘要: In this paper we describe a new approach for 2-D object segmentation using an automatic method applied on images with problems as partial information, overlapping objects, many objects in single scene, severe noise conditions and locating very high degree of deformation. We use physically-based shape model to obtain deformable template, which is defined canonical orthogonal coordinate system. The proposed methodology works starting from the output edge detector, processed automatically approximation shape. final estimation shapes obtained fitting template model, learned surface Results biological are presented.