Document conversion to editable formats (.doc, .rtf) assumes not only the whole text recognition but also document structure and layout retention. So OCR system has to analyze document content, extract and save into final document such elements as: headers, footers, page numbers, footnotes, table of contents, and others. Document formatting reconstruction is also necessary: font styles, text flows, tables and pictures formatting.
ABBYY FineReader Engine includes features for correct document conversion:
These features are supported by unique Document Structure API that provides access to all listed document elements. Developers are able to implement highly accurate and comprehensive document conversion application using ABBYY ADRT functionality.