2007/011 - Logical Document conversion: combining functional and formal knowledge
Hervé Dejean, Jean-Luc Meunier
Symposium on Document Engineering, Winnipeg, Canada, August 28-31, 2007.
We present in this paper a method for layout document analysis which uses an orthogonal and complementary view of the traditional formal view (how the element is made ?): we consider the objects we want to recognize in term of fucntion (what does it do ?). One key advantage of such functional knowledge is that the functions of some document elements are very stable from document to document and over the time. Relying on the stability of such functions, the method is not impacted by the layout variability, a key issue in logical document analysis and is thus very robust and versatile. The method starts the recognition process by using the functional knowledge and uses in a second step formal knowledge as a source of feedback in order to correct some errors. This allows the method to adapt itself to specific documents by using formal specificities.