Automatic knowledge extraction from OCR documents using hierarchical document analysis.
Mohammad MasumSai KosarajuTanju BayramogluGirish ModgilMingon KangPublished in: RACS (2018)
Keyphrases
- document analysis
- knowledge extraction
- document images
- printed documents
- document processing
- character recognition
- document image analysis
- electronic documents
- textual documents
- document image retrieval
- image analysis
- text analysis
- optical character recognition
- knowledge discovery
- word segmentation
- word recognition
- word level
- data mining
- database
- document collections
- machine vision
- pattern recognition
- metadata
- scanned documents
- real world