An information extraction system from patient historical documents
Eirini Matthaiou, Ergina Kavallieratou · 2012
Nowadays, document image retrieval systems are increasingly applicable by various businesses, governmental and academic organizations. ELEPAP (Hellenic Protection and Rehabilitation Centre for Disabled Children) is an organization which needs more efficient ways of managing its huge volume of archived documents. This paper deals with the preprocessing procedures of well-known OCR systems in order to extract specific features from ELEPAP's patients' cards. It is shown that our proposed methodology can provide good IT solutions for ELEPAP in order to extract information from its old archives.