Extraction of Tabular Data from Document Images

In this paper, we propose a heuristics-based method for automatic detection and extraction of tabular data from document images. The proposed approach utilizes page segmentation techniques, along with an OCR engine, in order to acquire the text data and bounding boxes of each word in the document. These elements are then grouped in a bottom-up fashion, based on a series of rules, in order to identify and reconstruct tabular arrangements of data. Based on this methodology, an open source cross-platform tool capable of recognizing the semantic structure of documents containing tabular data has been implemented, thus widening the range of document types than can be successfully converted into alternative accessible formats, suitable for users with visual impairments.