In this paper we propose a fast method for edge thinning and linking that consists of two phases. The first phase involves the integration of the edge structure by aggregating in a hierarchical manner the edge information contained in a relatively small collection of images of dierent edge densities. The second phase performs edge thinning and linking using the information associated with the endpoints of the aggregated edge results. The particular novelty of this approach lies in the labelling scheme which assigns the directionality of the endpoints based only on local knowledge. As a consequence, it relaxes the demand of a priori knowledge and furthermore assures an accurate and eÆcient search for edge paths in the image