Towards Digital Mathematical Library: Optical CharacterRecognition of Mathematical Texts
Petr Sojka, Július Štuller, Zdenka Linková · 2006
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\%.