BROWNIAN STRINGS - SEGMENTING IMAGES WITH STOCHASTICALLY DEFORMABLE CONTOURS

This paper describes an image segmentation technique in which an arbit rarily shaped contour was deformed stochastically until it fitted arou nd an object of interest. The evolution of the contour was controlled by a simulated annealing process which caused the contour to settle in to the global minimum of an image-derived ''energy'' function. The non parametric energy function was derived from the statistical properties of previously segmented images, thereby incorporating prior experienc e. Since the method was based on a state space search for the contour with the best global properties, it was stable in the presence of imag e errors which confound segmentation techniques based on local criteri a, such as connectivity. Unlike ''snakes'' and other active contour ap proaches, the new method could handle arbitrarily irregular contours i n which each interpixel crack represented an independent degree of fre edom. Furthermore, since the contour evolved toward the global minimum of the energy, the method was more suitable for fully automatic appli cations than the snake algorithm, which frequently has to be reinitial ized when the contour becomes trapped in local energy minima. High com putational complexity was avoided by efficiently introducing a random local perturbation in a time independent of contour length, providing control over the size of the perturbation, and assuring that resulting shape changes were unbiased. The method was illustrated by using it t o find the brain surface in magnetic resonance head images and to trac k blood vessels in angiograms.