*Active Contour

Segmentation > *Active Contour

Requires B/W Companion Image

Uses active contouring [1,2] to set the boundaries of each feature in the Companion Image based on the Current Image. Active contouring grows or shrinks features to “snap” them to locally high-contrast boundaries. The Contraction Bias allows users to add some external “force” to the contour to increase the likelihood that it will shrink.

1. Method

• Chan-Vese: Uses the Chan-Vese method to drive the contour [1]. Tends to work faster than the edge method.
• Edge: Uses the edge method to drive the contour [2]. Is naturally more biased to shrink the contour. Tends to work more slowly than the Chan-Vese method.

2. Max. Iterations

The maximum number of iterations to evolve the active contour

3. Smooth Factor

Controls the resulting roughness of the active contour. Higher is smoother.

4. Contraction Bias

Controls the external force on the active contour. Higher makes it tougher for the active contour to grow.

References

[1] T. F. Chan, L. A. Vese, Active contours without edges. IEEE Transactions on Image Processing, Volume 10, Issue 2, pp. 266-277, 2001

[2] V. Caselles, R. Kimmel, G. Sapiro, Geodesic active contours. International Journal of Computer Vision, Volume 22, Issue 1, pp. 61-79, 1997.