KNOWLEDGE FOR UNDERSTANDING TABLE-FORM DOCUMENTS

The issue about document structure recognition and document understand ing is today one of interesting subjects from a viewpoint of practical applications. The research objective is to extract the meaningful dat a from document images interpretatively and also classify them as the predefined item data automatically. In comparison with the traditional image-processing-based approaches, the knowledge-based approaches, wh ich make use of various knowledge in order to interpret structural/con structive features of documents, have been currently investigated as m ore flexible and applicable methods. In this paper, we propose a total ly integrated paradigm for understanding table-form documents from a v iewpoint of the architectural framework.