%0 Conference Proceedings
%T Field Extraction by hybrid incremental and a-priori structural templates
%A V. Poulain d'Andecy
%A Emmanuel Hartmann
%A Marçal Rusiñol
%B 13th IAPR International Workshop on Document Analysis Systems
%D 2018
%F V. Poulain d'Andecy2018
%O DAG; 600.084; 600.129; 600.121
%O exported from refbase (http://refbase.cvc.uab.es/show.php?record=3106), last updated on Thu, 28 Mar 2019 10:26:59 +0100
%X In this paper, we present an incremental framework for extracting information fields from administrative documents. First, we demonstrate some limits of the existing state-of-the-art methods such as the delay of the system efficiency. This is a concern in industrial context when we have only few samples of each document class. Based on this analysis, we propose a hybrid system combining incremental learning by means of itf-df statistics and a-priori genericmodels. We report in the experimental section our results obtained with a dataset of real invoices.
%K Layout Analysis
%K information extraction
%K incremental learning
%U http://refbase.cvc.uab.es/files/PHR2018.pdf
%U http://dx.doi.org/10.1109/DAS.2018.29
%P 251-256