Hauser SE, Le DX, Thoma GR
SPIE: Document Recognition and Retrieval VII. 2000 Jan;3976: 248-58.
The optical character recognition system (OCR) selected by the National Library of Medicine (NLM) as part of its system for automating the production of MEDLINE records frequently segments the scanned page images into zones which are inappropriate for NLM’s application. Software has been created in-house to correct the zones using character coordinate and character attribute information provided as part of the OCR output data. The software correctly delineates over 97 percent of the zones of interest tested to date.