Pattern matcher for OCR-corrupted documents and its evaluation.
Stefan AgneHans-Günther HeinPublished in: Document Recognition (1998)
Keyphrases
- printed documents
- document processing
- document collections
- scanned documents
- information retrieval
- document analysis
- information retrieval systems
- optical character recognition
- metadata
- keywords
- xml documents
- word spotting
- pattern matching
- document retrieval
- character recognition
- document clustering
- text documents
- web documents
- post processing
- xml retrieval
- error correction
- matching process
- relevance assessments
- document images
- page layout