In this paper, we introduce a new deformable model for image segmentation, by reformulating a region based active contours energy into a geodesic contour energy involving a Finsler metric. As a result, we solve the region based active contours energy minimization problem without resorting to level set functions, but using a robust Eikonal equation framework. By sampling a set of control points from the closed active contour in clockwise order, the active contours evolution problem is turned into finding a collection of minimal curves joining all the control points. Globally optimal minimal curves are obtained by solving an Eikonal equation, involving a Finsler metric, which is achieved at a modest numerical cost using a variant of the fast marching algorithm.
CITATION STYLE
Chen, D., Mirebeau, J. M., & Cohen, L. D. (2016). Finsler geodesics evolution model for region based active contours. In British Machine Vision Conference 2016, BMVC 2016 (Vol. 2016-September, pp. 22.1-22.12). British Machine Vision Conference, BMVC. https://doi.org/10.5244/C.30.22
Mendeley helps you to discover research relevant for your work.