Separating Indic Scripts with 'matra' - A Precursor to Script Identification in Multi-script Documents.
Sk Md ObaidullahChitrita GoswamiK. C. SantoshChayan HalderNibaran DasKaushik RoyPublished in: CVIP (1) (2016)
Keyphrases
- document collections
- information retrieval
- legal documents
- xml documents
- metadata
- information retrieval systems
- document retrieval
- database
- document clustering
- relevant documents
- arabic documents
- indian languages
- web documents
- text documents
- keywords
- machine learning
- retrieval systems
- document content
- document level
- document classification
- ranked list
- document representation
- text analysis
- retrieved documents
- multi document summarization
- multimedia documents
- textual content
- free text
- digital documents
- website
- web pages