Table analysis is a complex problem, involving searching solutions from a large search space. Studies show that finding the most credible answers to complex problems often require combining multiple kinds of knowledge. Although the literature shows that both layout and language information have been used in table extraction systems, the amount of information each system uses is limited, and up till now, there is not an easy, systematic way to incorporate new information in these systems. This paper describes a framework for combining multiple solutions (including partial solutions) to solve a general table recognition problem.
Copyright 2009 IEEE. Reprinted from ICDAR '09 : Proceedings of the 10th International Conference on Document Analysis and Recognition, 26-29 July 2009, Barcelona, Catalonia, Spain. This material is posted here with permission of the IEEE. Such permission of the IEEE does not in any way imply IEEE endorsement of any of Macquarie University’s products or services. Internal or personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution must be obtained from the IEEE by writing to firstname.lastname@example.org. By choosing to view this document, you agree to all provisions of the copyright laws protecting it.