Resumen de Contextual System of Symbol Structural Recognition based on an Object-Process Methodology

Mathieu Delalandre, Eric Trupin, Jean-Marc Ogier, Jacques Labiche

• We present in this paper a symbol recognition system for the graphic documents. This one is based on a contextual approach for symbol structural recognition exploiting an Object-Process Methodology. It uses a processing library composed of structural recognition processings and contextual evaluation processings. These processings allow our system to deal with the multi-representation of symbols. The different processings are controlled, in an automatic way, by an inference engine during the recognition process. The factual, strategic, and descriptive knowledge are structured according to an Object-Process Methodology of the considered recognition application. The representation of symbols are then adapted during the recognition process according to their classes. This original approach for knowledge structuring allows especially the strategic and descriptive knowledge combination which increases the recognition abilities of system. We present results of this system on the GREC2003 contest of symbol recognition.