Summary: Digital Object Identifier (DOI) 10.1007/s10032-002-0080-x
IJDAR (2002) 5: 1­16
Document understanding for a broad class of documents
Marco Aiello1,2
, Christof Monz2
, Leon Todoran1
, Marcel Worring1,
1
Intelligent Sensory Information Systems, University of Amsterdam, Kruislaan 403, 1098 SJ Amsterdam, The Netherlands
2
Institute for Logic, Language and Computation, University of Amsterdam, Plantage Muidergracht 24,
1018 TV Amsterdam, The Netherlands
e-mail: {aiellom,christof,todoran,worring}@science.uva.nl; http://www.science.uua.nl/aiellom,christof,todoran,worring
Received: March 15, 2001 / Revised version: March 18, 2002
Abstract. We present a document analysis system able
to assign logical labels and extract the reading order in
a broad set of documents. All information sources, from
geometric features and spatial relations to the textual
features and content are employed in the analysis. To
deal effectively with these information sources, we define

Source: Aiello, Marco - Institute for Mathematics and Computing Science, Rijksuniversiteit Groningen
Monz, Christof - Research Institute Computer Science, Universiteit van Amsterdam

Collections: Computer Technologies and Information Sciences