Eighth International Conference on Document Analysis and Recognition (ICDAR'05)
Handwritten Document Segmentation Using Hidden Markov Random Fields
Seoul, Korea
August 31-September 01
ISBN: 0-7695-2420-6
Stephane Nicolas, PSI FRE CNRS Universite de Rouen UFR des Sciences et Techniques, France
Yousri Kessentini, PSI FRE CNRS Universite de Rouen UFR des Sciences et Techniques, France
Thierry Paquet, PSI FRE CNRS Universite de Rouen UFR des Sciences et Techniques, France
Laurent Heutte, PSI FRE CNRS Universite de Rouen UFR des Sciences et Techniques, France
In this paper we present a method based on Hidden Markov Random Fields and 2D dynamic programming image decoding, for segmenting pages of complex handwritten manuscripts such as novelist drafts. After a formal description of the theoretical framework and the principles of the decoding method, we describe the implementation of the model and the decoding method. Then we discuss the results obtained with this approach on the drafts of the French novelist Gustave Flaubert.
Citation:
Stephane Nicolas, Yousri Kessentini, Thierry Paquet, Laurent Heutte, "Handwritten Document Segmentation Using Hidden Markov Random Fields," icdar, pp.212-216, Eighth International Conference on Document Analysis and Recognition (ICDAR'05), 2005