Using OCR and equalization to downsample documents.
Oscar E. AgazziKenneth Ward ChurchWilliam A. GalePublished in: ICPR (2) (1994)
Keyphrases
- document processing
- printed documents
- scanned documents
- optical character recognition
- document analysis
- page layout
- document collections
- information retrieval
- ocr systems
- document images
- information retrieval systems
- document image retrieval
- web documents
- text documents
- word spotting
- character recognition
- document classification
- scanned images
- free text
- document retrieval
- text recognition
- post processing
- document clustering
- relevant documents
- user queries
- structured documents
- keywords
- document type
- database
- text analysis
- electronic documents
- document content
- preprocessing
- multipath
- query terms
- recognition errors
- metadata