Fovea segmentation in fluorescein angiographies is a fundamental first task in any study of ocular diseases. The importance of fovea detection is due to the fact that the nearer the center of the fovea a lesion is, the graver this lesion is. The proposed method is based on B-snakes and uses a greedy algorithm to minimize an appropriate energy, which accurately leads to a convenient characterization of the boundary of the foveal zone. A first initialization step which consists of finding the most appropriate local minimum along with a procedure to construct an initial contour involving a region growing algorithm, lead to a convenient and robust initialization of the proposed active contour model. 1