In this paper a new method that incorporates moment-based shape information into geometric active contours is presented. As any shape may theoretically be characterized by its set of moments, the shape prior is represented based on Legendre moments. By combining the shape prior with the powerful geometric active contours proposed by Chan and Vese, the improved model can retain all the advantage of the Chan-Vese model and have the additional ability of being able to compactly represent global shape of an object. Experiments on synthetic and real image segmentation show the efficiency of our method.