In this paper, we evaluate and systematically compare two different (multi-)relational learning methods based on a statistical approach and a logical approach for the task of document image understanding. For a fair comparison, both methods are tested on the same real world dataset consisting of multipage articles published in an international journal. An analysis of pros and cons of both approaches is reported.
Citation:
Michelangelo Ceci, Margherita Berardi, Donato Malerba, "Relational Learning techniques for Document Image Understanding: Comparing Statistical and Logical approaches," icdar, pp.473-477, Eighth International Conference on Document Analysis and Recognition (ICDAR'05), 2005