Skeletonization by a topology-adaptive self-organizing neural network

A self-organizing neural network model is proposed to generate the skeleton of a pattern. The proposed neural net is topology-adaptive and has a few a dvantages over other self-organizing models. The model is dynamic in the se nse that it grows in size over time. The model is especially designed to pr oduce a vector skeleton of a pattern. It works on binary patterns, dot patt erns and also on gray-level patterns. Thus it provides a unified approach t o skeletonization. The proposed model is highly robust to noise (boundary a nd interior noise) as compared to existing conventional skeletonization alg orithms and is invariant under arbitrary rotation. It is also efficient in medial axis representation and in data reduction. (C) 2001 Pattern Recognit ion Society. Published by Elsevier Science Ltd. All rights reserved.