Back      Top     Next                   Kolloquium - DVI - F.Leymarie

Image Segmentation By Reaction-Diffusion Bubbles

Benjie Kimia & Huseyin Tek

The approach is motivated by a shock-based morphogenetic language where the growth of 4 types of shocks results in a complete description of shape. Specifically, objects are randomly hypothesized in the form of fourth-order shocks (seeds) which then grow, merge, split, shrink and in general deform under physically motivated ``forces'', but slow down and come to a halt near differential structures.

Two major issues arise in the segmentation of 3D images using this approach.

1. First, it is shown that the segmentation of 3D images by 3D bubbles is superior to a slice-by-slice segmentation by 2D bubbles or by ``2(1/2)D bubbles'' which are inherently 2D but use 3D information for their deformation. Specifically, the advantages lie in an intrinsic treatment of the underlying geometry and accuracy of reconstruction.
2. Second, gaps and weak edges which frequently present a significant problem for 2D and 3D segmentation, are regularized by curvature-dependent curve and surface deformations which constitute diffusion processes.

The 3D bubbles evolving in the 3D reaction-diffusion space are a powerful tool in the segmentation of medical and other images, as illustrated for several realistic examples.

2D Segmentation Results:
 
   1.  A Laser Range Image:
 
    2.  A FLIR Image:
 
    3. Role Of Diffusion:

 
3D Segmentation Results:
 
    1. Carotid Arteries:

    2. White Matter:

Back      Top     Next