|<< 1 >>
|Francisco Alvaro; Francisco Cruz; Joan Andreu Sanchez; Oriol Ramos Terrades; Jose Miguel Benedi
|Structure Detection and Segmentation of Documents Using 2D Stochastic Context-Free Grammars
|document image analysis; stochastic context-free grammars; text classication features
|In this paper we dene a bidimensional extension of Stochastic Context-Free Grammars for structure detection and segmentation of images of documents.
Two sets of text classication features are used to perform an initial classication 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 Models
and the results showed that the proposed grammatical model outperformed
the other methods. Furthermore, grammars also provide the document structure
along with its segmentation.
|Place of Publication
|Abbreviated Series Title
|DAG; 601.158; 600.077; 600.061
|Admin @ si @ ACS2015
|Permanent link to this record