Extraction and classification of graphical symbol candidates based on perceptual organization

A general-purpose graphical symbol extraction method is proposed in which the visual characteristics of graphical symbols are used. The graphical symbols are modeled as gatherings of short line segments and loops. Based on these models, two different methods are applied in parallel to a diagram, and two results are generated and integrated into the candidates. Further, a method to classify the extracted graphical symbol candidates by comparing their shape and structure is described. An important point of the method is that no a priori knowledge of the diagram under consideration is introduced, hence the method is applicable to a wide range of diagrams