An Intelligent Document Understanding & Reproduction System
Michael Sharpe, Nizam Ahmed, Geoff Sutcliffe · 1994
This paper presents the design and implementation of an intelligent document understanding and reproduction system. The system analyses a printed document to create an electronic document. The electronic document is written in a standard typesetting language (LaTeX), and is thus human usable. The output from processing the electronic document closely resembles the original printed document. A new document understanding technique, which utilises the Definite Clause Grammar formalism, has been developed.