A Short Guide on a Fast Global Minimization Algorithm for Active Contour Models

This is a short guide to explain how to quickly minimize a large class of segmentation models called active contours. We believe that the proposed theory and algorithm, introduced in a series of papers [6, 4, 10, 11], produce so far one of the most efficient minimization methods for the active contour segmentation problem. For example, the well-know cameraman picture, which size is 256× 256, is segmented in less than 0.1 seconds. We also compare our algorithm with the popular and fast graph-cuts technique [2, 9]. We show that our algorithm, while being easier to code, produces results slightly faster than graph-cuts. Besides, our algorithm is more accurate than graph-cuts because it uses isotropic schemes to regularize the contour and is sub-pixel precise. Finally, the memory requirement is low. 1 General Active Contour Model The general energy minimization problem for any (two-phase) active contour model is as follows: min C { FAC(C) = ∫