Abstract Though the Visible Human Dataset provides a complete
volumic coverage of the human body, it does not give information about
its structure. An important task is to identify the spatial extents of
the organs of interest, and to provide their surface models. In this paper,
we will present two methods for the reconstruction of organs from the Visible
Human Dataset. The first method is the segmentation of organ on each slice
with the snake technique. The second method uses the Shape Constrained
Deformable Model. For these two methods, we present testing results of
the extraction of different types of organ from the Visible Human Data.
Keywords: 3D reconstruction, segmentation,
snakes.
