TY  - JOUR
AU  - Francisco Alvaro
AU  - Francisco Cruz
AU  - Joan Andreu Sanchez
AU  - Oriol Ramos Terrades
AU  - Jose Miguel Benedi
PY  - 2015//
TI  - Structure Detection and Segmentation of Documents Using 2D Stochastic Context-Free Grammars
T2  - NEUCOM
JO  - Neurocomputing
SP  - 147
EP  - 154
VL  - 150
IS  - A
KW  - document image analysis
KW  - stochastic context-free grammars
KW  - text classication features
N2  - In this paper we dene a bidimensional extension of Stochastic Context-Free Grammars for structure detection and segmentation of images of documents.Two sets of text classication features are used to perform an initial classication of each zone of the page. Then, the document segmentation is obtained as the most likely hypothesis according to a stochastic grammar. We used a dataset of historical marriage license books to validate this approach. We also tested several inference algorithms for Probabilistic Graphical Modelsand the results showed that the proposed grammatical model outperformedthe other methods. Furthermore, grammars also provide the document structurealong with its segmentation.
L1  - http://refbase.cvc.uab.es/files/ACS2014.pdf
N1  - DAG; 601.158; 600.077; 600.061
ID  - Francisco Alvaro2015
ER  -