A Very Efficient Table Detection System from Document Images.
Sekhar Mandal, S. P. Chowdhury, Amit Kumar Das, Bhabatosh Chanda · Indian Conference on Computer Vision, Graphics and Image Processing · 2004
The requirement of detection and identification of tables from document images is crucial to any document image analysis and digital library system. Here in this paper we report a very simple but extremely powerful approach to detect any table in any form that may be present in a document page. The algorithm rely on the observation that the tables has distinct columns whose physical implication is in the presence of substantially larger gaps between the fields than the gaps between the words in text lines. This deceptively simple observation has led to the design of a simple but powerful table detection system with a low computation cost and achieving an efficiency close to 100%. Moreover, mathematical foundation of the approach is also established including formation of a regular expression for ease of implementation.