An Empirical Comparison of Neural Techniques Linking of Images for Edge

Edge linking is a fundamental computer vision task, yet presents d@culties arising from the lack of information in the image. Viewed as a constrained optimisation problem, it is NP hard being isomorphic to the classical travelling salesman problem. Self-learning neural techniques boast the ability to solve hard, ill-dejned problems, and hence offer promise for such an application. This paper examines the suitability of four well-known unsupervised techniques for the task of edge linking, by applying them to a test bed of edge point images and then evaluating their petiormance both quantitatively and qualitatively. Techniques studied are the elastic net, active contours, Kohonen map and Burr’s modified elastic net. Of these, only the elastic net and the Kvhonen map are realistic contenders for general edge-linking tasks. However, the other two exhibit behaviour which may make them particularly suited to some specific image-processing and computer vision applications.