LAYOUT RECOGNITION OF MULTI-KINDS OF TABLE-FORM DOCUMENTS

Many approaches have reported that knowledge-based layout recognition methods are very successful to classify the meaningful data from docum ent images automatically. However, these approaches are applicable to only the same kind of documents because they are based on the paradigm that specifies the structure definition information in advance so as to be able to analyze a particular class of documents intelligently. I n this paper, we propose a method to recognize the layout structures o f multi-kinds of table-form document images. For this purpose, we intr oduce a classification tree to manage the relationships among differen t classes of layout structures. Our recognition system has two modes: layout knowledge acquisition and layout structure recognition. In the layout knowledge acquisition mode, table-form document images are dist inguished according to this. classification tree and then the structur e description trees which specify the logical structures of table-form documents are generated automatically. While, in the layout structure recognition mode, individual item fields in the table-form document i mages are extracted and classified successfully by searching the class ification tree and interpreting the structure description tree.