Abstract.
Recovering the shape of a class of ob jects requires estab- lishing correct correspondences between manually or automatically an- notated landmark points. In this study, we utilise a novel approach to automatically recover the shape of hand outlines from a series of 2D train- ing images. Automated landmark extraction is accomplished through the use of the self-organising model the growing neural gas (GNG) network which is able to learn and preserve the topological relations of a given set of input patterns without requiring a priori knowledge of the structure of the input space. To measure the quality of the mapping throughout the adaptation process we use the topographic product. Results are given for the training set of hand outlines.