A Unified Algorithm for Identification of Various Tabular Structures from Document Images

Abstract

This paper presents a unified algorithm for segmentation and identification of various tabular structures from document page images. Such tabular structures include conventional tables and displayed math-zones, as well as Table of Contents (TOC) and Index pages. After analyzing the page composition, the algorithm initially classifies the input set of document pages into tabular and non-tabular pages. A tabular page contains at least one of the tabular structures, whereas a non-tabular page does not contain any. The approach is unified in the sense that it is able to identify all tabular structures from a tabular page, which leads to a considerable simplification of document image segmentation in a novel manner. Such unification also results in speeding up the segmentation process, because the existing methodologies produce time-consuming solutions for treating different tabular structures as separate physical entities. Distinguishing features of different kinds of tabular structures have been used in stages in order to ensure the simplicity and efficiency of the algorithm and demonstrated by exhaustive experimental results.