DOI:
Abstract:
A rule-based system to make inferences about document images is introduced. Given a digitized document image, the system controls the analysis of the document, and identifies all the different printed regions in the document image. Logical "blocks" of information on the document image are interpreted and classified by this system which then produces as output an editable description of the entire document. The system uses a goal-directed top down appoach, and utilizes a three-level rule hierarchy to implement its control strategy.