Semi-automated document image clustering and retrieval.
Markus DiemFlorian KleberStefan FielRobert SablatnigPublished in: DRR (2014)
Keyphrases
- semi automated
- document images
- document analysis
- document image analysis
- document processing
- page segmentation
- fully automated
- scanned documents
- handwritten documents
- word level
- information retrieval systems
- clustering algorithm
- k means
- document image understanding
- language identification
- digital libraries
- information retrieval
- indian languages
- optical character recognition
- document retrieval
- image retrieval
- scanned images
- page layout
- retrieval model
- retrieval systems
- historical documents
- scanned document images
- printed documents
- test collection
- relevance feedback
- image segmentation