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, Isosurfaces, T-Surfaces) for segmentation of grey level images.
Unable to display preview. Download preview PDF.
- 1.Bruce, J., Balch, T., Veloso, M.: Fast and inexpensive color image segmentation for interactive robots (2000)Google Scholar
- 2.Chiang, Y.-J., Farias, R., Silva, C., Wei, B.: A unified infrastructure for parallel out-of-core isosurface and volume rendering of unstructured grids. IEEE Parallel and Large-Data Vis. and Graph. (2001)Google Scholar
- 3.Chiang, Y.-J., Silva, C., Schroeder, W.J.: Interactive out-of-core isosurface extraction. IEEE Visualization, 67–174 (1998)Google Scholar
- 7.McInerney, T., Terzopoulos, D.: Deformable models in medical image analysis: A survey. Medical Image Analysis 1(2) (1996)Google Scholar
- 9.Strauss, E., Jimenez, W., Giraldi, G.A., Silva, R., Oliveira, A.F.: A semiautomatic surface reconstruction framework based on t-surfaces and isosurface extraction methods. In: International Symposium on Computer Graphics, Image Processing and Vision, SIBGRAPI (2002)Google Scholar