Page Segmentation of Structured Documents Using 2D Stochastic Context-Free Grammars.
Francisco AlvaroFrancisco CruzJoan-Andreu SánchezOriol Ramos TerradesJosé-Miguel BenedíPublished in: IbPRIA (2013)
Keyphrases
- structured documents
- page segmentation
- stochastic context free grammars
- comparative evaluation
- hidden markov models
- document images
- storage and retrieval
- bayesian networks
- information retrieval systems
- xml documents
- optical character recognition
- web pages
- information retrieval
- evaluation methods
- web documents
- document structure
- complex events
- query language
- relevant documents
- context free grammars
- parse tree
- contextual information
- database