TABLE-FORM STRUCTURE-ANALYSIS BASED ON BOX-DRIVEN REASONING

Table-form document structure analysis is an important problem in the document processing domain. This paper presents a new method called Bo x-Driven Reasoning (BDR) to robustly analyze the structure of table-fo rm documents that include touching characters and broken lines. Real d ocuments are copied repeatedly and overlaid with printed data, resulti ng in characters that touch cells and lines that are broken. Most prev ious methods employ a line-oriented approach, but touching characters and broken lines make the procedure fail at an early stage. BDR deals with regions directly in contrast with other previous methods and a re duced resolution image is introduced to supplement information deterio rated by noise. Experimental tests show that BDR reliably recognizes c ells and strings in document images with touching characters and broke n lines.