Text and metadata extraction from scanned Arabic documents using support vector machines.
Wenda QinRanda I. ElanwarMargrit BetkePublished in: J. Inf. Sci. (2022)
Keyphrases
- metadata extraction
- digital libraries
- metadata
- content features
- arabic documents
- information retrieval
- document images
- character n grams
- document level
- keywords
- text mining
- text documents
- document analysis
- sentence level
- database
- text data
- n gram
- text retrieval
- natural language
- word spotting
- web pages
- search engine
- databases