Robust table-form structure analysis based on box-driven reasoning

TitleRobust table-form structure analysis based on box-driven reasoning
Publication TypeConference Papers
Year of Publication1995
AuthorsHori O, Doermann D
Conference NameDocument Analysis and Recognition, 1995., Proceedings of the Third International Conference on
Date Published1995/08//
Keywordsanalysis;table, analysis;touching, BDR;box, characters;character, document, domain;robust, driven, form, image, images;document, lines;document, mechanisms;, PROCESSING, processing;inference, reasoning;broken, recognition;data, structure, structures;document, table

Table form document structure analysis is an important problem in the document processing domain. The paper presents a method called Box Driven Reasoning (BDR) to robustly analyze the structure of table form documents which include touching characters and broken lines. Most previous methods employ a line oriented approach. Real documents are copied repeatedly and overlaid with printed data, resulting in characters which touch cells and lines which are broken. BDR deals with regions directly, in contrast with other previous methods. Experimental tests show that BDR reliably recognizes cells and strings in document images with touching characters and broken lines