Publication details

OCRMiner

Authors

HA Hien Thi HORÁK Aleš MEDVEĎ Marek NEVĚŘILOVÁ Zuzana

MU Faculty or unit

Faculty of Informatics

Description The aim of the OCRMiner project is to use natural language processing technologies for extracting information from financial documents. At first stage, a document has to be classified, i.e. it has to be decided whether it is a financial document (invoice, proforma invoice). Second step is information extraction and detection of meaning of a particular information, i.e. classification into classes such as buyer, seller, due date.
Related projects: