Reduction of Bleed-through in Scanned Manuscript Documents.
Eric DuboisAnita PathakPublished in: PICS (2001)
Keyphrases
- document images
- document analysis
- scanned documents
- scanned document images
- information retrieval
- document collections
- information retrieval systems
- web documents
- scanned images
- document retrieval
- document classification
- metadata
- document clustering
- vector space model
- distributed information retrieval
- text documents
- keywords
- text lines
- legal documents
- xml documents
- database
- free text
- web data
- query terms
- digital objects
- text analysis
- time stamped
- plagiarism detection
- vector space