%0 Conference Proceedings
%T Hybrid grammar language model for handwritten historical documents recognition
%A Nuria Cirera
%A Alicia Fornes
%A Volkmar Frinken
%A Josep Llados
%B 6th Iberian Conference on Pattern Recognition and Image Analysis
%D 2013
%V 7887
%I Springer Berlin Heidelberg
%@ 0302-9743
%@ 978-3-642-38627-5
%F Nuria Cirera2013
%O DAG; 602.006; 600.045; 600.061
%O exported from refbase (http://refbase.cvc.uab.es/show.php?record=2292), last updated on Thu, 10 Nov 2016 12:03:02 +0100
%X In this paper we present a hybrid language model for the recognition of handwritten historical documents with a structured syntactical layout. Using a hidden Markov model-based recognition framework, a word-based grammar with a closed dictionary is enhanced by a character sequence recognition method. This allows to recognize out-of-dictionary words in controlled parts of the recognition, while keeping a closed vocabulary restriction for other parts. While the current status is work in progress, we can report an improvement in terms of character error rate.
%U http://refbase.cvc.uab.es/files/CFF2013.pdf
%U http://dx.doi.org/10.1007/978-3-642-38628-2_13
%P 117-124