Variational bspline level-set method for fast image segmentation
Lists
Only you see this
Abstract
In the field of image segmentation, most of level-set-based active contour approaches are based on a discrete represen-tation of the associated implicit function. We present in this paper a different formulation where the level-set is modelled as a continuous parametric function expressed on a B-spline basis. Starting from the Mumford-Shah energy functional, we show that this formulation allows computing the solution as a restriction of the variational problem on the space spanned by the B-splines. As a consequence, the minimization of the functional is directly obtained in terms of the B-splines pa-rameters. We also show that each step of this minimization may be expressed through a convolution operation. Because the B-spline functions are separable, this convolution may in turn be performed as a sequence of simple 1D convolutions, which yields a very efficient algorithm. The behaviour of this approach is illustrated on biomedical images from vari-ous fields. Index Terms — Level-set, B-spline, Variational methods 1.
BibTeX
@inproceedings{bernard2008variational,
author = {O. Bernard and D. Friboulet and P. Thevenaz and Michaël Unser},
title = {{Variational bspline level-set method for fast image segmentation}},
booktitle = {ISBI},
year = {2008},
doi = {10.1109/isbi.2008.4540961},
}Loading related content...