Logical structure recognition of diagram images

Abstract

This document presents a method of a logical links structure recognition between elements on diagrams. The applied approach intuitively mimics a human way of recognition that relies on merging already found connectors into more complex ones. This procedure is modeled by our method where simple and obvious connectors and gradually extended to more complex structures. Each iteration may lead to modification of connectors set obtained so far. The modifications are managed by a rules set describing logical and graphical constraints that should be satisfied by the connectors structure. If the extension leads to violation of constraints defined by the rules then the modification is not carried out. In this way, the recognized diagram structure is consistent with the assumed principles. The method was experimentally validated using the set of diagrams from three domains. In conclusions, method's advantages and drawbacks are discussed.