Keyphrases
- textual documents
- document processing
- digital libraries
- multimedia documents
- document images
- printed documents
- document image analysis
- multimedia
- united states
- optical character recognition
- preprocessing
- post processing
- character recognition
- census data
- text recognition
- authorship attribution
- data swapping
- recognition errors
- information retrieval
- handwriting recognition
- document analysis
- language independent
- ranked list
- document collections
- feature selection