COMBINING SOURCES OF EVIDENCE TO RESOLVE AMBIGUITIES IN TOPONYM RECOGNITION IN CARTOGRAPHIC MAPS
Alexander F. Gelbukh, Sangyong Han, Serguei Levachkine · 2003
Graphical documents such as cartographic maps contain a great variety of textual elements appearing in diff erent spatial positions, in different fonts, sizes, and c olors, touching and overlapping graphical symbols. This greatly complicates automatic optical recognition of such t extual elements in the process of raster-to-vector convers ion of graphical documents. In this work, we propose a method that combines OCR-based text recognition in rasterscanned maps with heuristics specially adapted for cartographic data to resolve the recognition ambigu ities using various sources of evidence. Our goal is to f orm in the vector thematic layers geographically meaningfu l words correctly attached to the cartographic object s.