Symbols recognition by global-local structural approaches, based on the scenarios use,and with a XML representation of data

This paper deals with the structural recognition ofsymbols on the documents. We have based our system ona combination of local and global structural approaches.The global approach groups the connected componentstogether according to some closeness and connectionconstraints. The local approach splits up each connectedcomponent into a graph of geometrical objects (vectors,arcs, curves). The extracted graphs are matched thanks toa structural classifier, which permits graph-subgraph andexact-inexact matching. The system adaptability isobtained thanks to the scenarios use. A XML datarepresentation is used, allowing the data manipulationsand the graphic representations of results.