Translating Diagrams

Computer programs have to “understand” diagrams if diagrams are going to be used for communications with or through the computer, i.e., the computer has to be supplied with a method that translates a diagram into an abstract internal representation for further processing. This paper describes such a method that is based on a specification of the translation process. The translation process starts with a diagram, which is simply represented as a collection of atomic diagram components, and it ends up with a hypergraph as a semantic or abstract syntax representation of the diagram. The specification of the translation process mainly consists of two parts: the specification of spatial relationships between atomic diagram components in terms of their numeric parameters (e.g., position, size), and a translation grammar that describes the concrete diagram syntax as well as the rules for generating the semantic or abstract syntax representation.