This paper presents particularly a contextual post processing subsystem for a Turkish machine printed character recognition system. The contextual post processing subsystem is based on positional binary 3- gram statistics for Turkish language, an error corrector parser and a lexicon, which contains root words and the inflected forms of the root words. Error corrector parser is used for correcting CR alternatives using Turkish Morphology.
Citation:
Sait Ulas Korkmaz, G. Kir?i?egi Y. Akinci, Volkan Atalay, "A Character Recognizer for Turkish Language," icdar, vol. 2, pp.1238, Seventh International Conference on Document Analysis and Recognition (ICDAR'03) - Volume 2, 2003