On Separation of English Numerals from Multilingual Document Images.
Basanna V. DhandraMallikarjun HangargePublished in: J. Multim. (2007)
Keyphrases
- document images
- indian languages
- language identification
- cross language
- cross lingual
- cross language ir
- optical character recognition
- word level
- cross language information retrieval
- language resources
- multi lingual
- language specific
- multilingual information retrieval
- document image analysis
- parallel corpus
- document analysis
- document image understanding
- language independent
- document processing
- printed documents
- scanned documents
- machine translation
- mathematical formulas
- question answering
- scanned document images
- page segmentation
- machine translation system
- digital libraries
- natural language
- storage and retrieval
- word spotting
- line extraction
- information extraction
- historical documents
- page layout
- image analysis
- image processing