Towards Digital Mathematical Library: Optical Character Recognition of Mathematical Texts

Warning

This publication doesn't include Faculty of Arts. It includes Faculty of Informatics. Official publication website can be found on muni.cz.

Authors	SOJKA Petr ŠTULLER Julius LINKOVÁ Zdenka
Year of publication	2006
Type	Article in Proceedings
Conference	Inteligentní modely, algoritmy a nástroje pro vytváření sémantickeho webu
MU Faculty or unit	Faculty of Informatics
Citation
Web	Full paper--proceedings
Field	Documentation, library studies, information management
Keywords	OCR; Optical Character Recognition; DML-CZ; digitization; Digital mathematics library project
Description	This paper describes a prototype of the OCR math engine built in the DML-CZ project. Solution stands on the combination of FineReader and InftyReader programmes. The achieved error rate (counting not only character errors, but also errors in the recognition of structure of mathematics notation) decreased from an initial 12\% to under 1\%.
Related projects:	DML-CZ: Czech Digital Mathematical Library Intelligent Models, Algorithms, Methods and Tools for the Semantic Web (realization)