TY  - CONF
AU  - Francisco Alvaro
AU  - Francisco Cruz
AU  - Joan Andreu Sanchez
AU  - Oriol Ramos Terrades
AU  - Jose Miguel Bemedi
A2  - IbPRIA
PY  - 2013//
TI  - Page Segmentation of Structured Documents Using 2D Stochastic Context-Free Grammars
T2  - LNCS
BT  - 6th Iberian Conference on Pattern Recognition and Image Analysis
SP  - 133
EP  - 140
VL  - 7887
PB  - Springer Berlin Heidelberg
N2  - In this paper we define a bidimensional extension of Stochastic Context-Free Grammars for page segmentation of structured documents. Two sets of text classification features are used to perform an initial classification of each zone of the page. Then, the page segmentation is obtained as the most likely hypothesis according to a grammar. This approach is compared to Conditional Random Fields and results show significant improvements in several cases. Furthermore, grammars provide a detailed segmentation that allowed a semantic evaluation which also validates this model.
SN  - 0302-9743
SN  - 978-3-642-38627-5
L1  - http://refbase.cvc.uab.es/files/ACS2013.pdf
UR  - http://dx.doi.org/10.1007/978-3-642-38628-2_15
N1  - DAG; 605.203
ID  - Francisco Alvaro2013
ER  -