Out-of-core segmentation by deformable models

Memory limitations can lower the performance of segmentation applications for large images or even make it undoable. In this paper we address this problem through out-of-core techniques. Specifically, we integrate the T-Surfaces model, and out-of-core isosurface generation methods in a general framework for segmentation of large image volumes. T-Surfaces is a parametric deformable model based on a triangulation of the image domain, a discrete surface model and an image threshold. Isosurface generation techniques have been implemented through an out-of-core method that uses a k-d-tree-like structures, called meta-cell technique. By using the meta-cell framework, we present an out-of-core version of a segmentation method based on T-Surfaces and isosurface extraction. We demonstrate our out-of-core methodology (Meta-Cell, Iso-surfaces, T-Surfaces) for segmentation of grey level images.