Automatic Learning of Symbol Descriptions Avoiding Topological Ambiguities

Abstract

In this paper we address both automatic recognition of sketched symbols and the construction of the corresponding models from user drawn examples. Our approach is based on a two stage process. In a first phase we use an Adjacency Grammar to express topological properties of the symbol. In order to be able to further disambiguate topologically similar configurations on the rules of the grammar that are triggered by the recognition process produce a set of local geometric invariants is defined. The combination of both steps results in an efficient recognition method for user drawn sketches. Furthermore, we show that the same approach can easily be adapted for the generation of Adjacency Grammars from user provided and hand drawn examples.