We describe how to teach deformable models to recognize segmentation correctness based on user-specified criteria, and we present a method for evaluating which criteria work best. We present sectored snakes, a formulation that demonstrably improves upon regular snakes.
A traditional deformable model (``snake'' in 2D), used for image segmentation, fails to find an object's boundary when the strongest nearby image edges are not the ones sought. But models can be trained to respond to other image features instead, by building their probability distribution. The implementor must then decide on which of many image qualities to teach the model. To this end, we show how to evaluate the efficacy of any resulting deformable model, given a sampling of ground truth, a model of the range of shapes tried during optimization, and a measure of shape closeness.
In the domain of abdominal CT images, we demonstrate such evaluation on a ``sectoring'' of a snake, in which intensity and perpendicular gradient are observed over equal-length segments. This specific set of qualities shows a measured improvement over an objective function that is uniform around the shape, and it follows naturally from examination of the latter's failures due to images variations around the organ boundary.
Keywords: Segmentation and Grouping, Shape Representation and Recovery, Learning in Vision, Applications, Segmentation Evaluation
This work was supported in part by DOD/ONR MURI Grant N00014-95-1-0601, by the New York State Science and Technology Foundation, and by ARPA Contract DACA-76-92-C-007.
Entire article as a PostScript file: short version (1 Meg), long version (2 Meg).
Samuel D. Fenster
Department of Computer Science
Columbia University