Indexing and retrieval of words in old documents.
Simone MarinaiEmanuele MarinoGiovanni SodaPublished in: ICDAR (2003)
Keyphrases
- index terms
- word spotting
- document indexing
- information retrieval
- controlled vocabulary
- handwritten documents
- handwritten document images
- retrieval engine
- document space
- document representation
- document collections
- document retrieval
- document analysis
- information retrieval systems
- text retrieval
- retrieval process
- effective retrieval
- document content
- historical documents
- retrieval strategies
- vector space model
- arabic documents
- retrieval systems
- content based retrieval
- text queries
- document processing
- word frequency
- text documents
- stop words
- chinese text retrieval
- multimedia documents
- document level
- structured documents
- word segmentation
- interactive retrieval
- retrieve documents
- keywords
- related documents
- metadata
- relevant documents
- efficient retrieval
- indexing techniques
- automatic indexing
- retrieval model
- query expansion
- content based indexing
- document image retrieval
- image retrieval
- search engine
- vector space
- tf idf
- term frequency
- text mining
- digital libraries
- historical manuscripts
- semantic content
- multiword