Identification of Indic Scripts on Torn-Documents.
Sukalpa ChandaKatrin FrankeUmapada PalPublished in: ICDAR (2011)
Keyphrases
- information retrieval
- document collections
- information retrieval systems
- web documents
- document clustering
- metadata
- xml documents
- relevant documents
- database
- text documents
- retrieval systems
- semantic relationships
- textual content
- legal documents
- user queries
- co occurrence
- document retrieval
- electronic documents
- ranked list
- free text
- document classification
- vector space
- document content
- word recognition
- document analysis
- scripting language
- vector space model
- web data
- text retrieval
- query terms
- keywords
- website
- machine learning
- neural network