Results of Applying Probabilistic IR to OCR Text.
Kazem TaghvaJulie BorsackAllen ConditPublished in: SIGIR (1994)
Keyphrases
- information retrieval
- text retrieval
- text recognition
- optical character recognition
- printed documents
- text extraction
- document processing
- ocr systems
- document images
- page layout
- information retrieval systems
- document analysis
- probabilistic retrieval
- bayesian networks
- post processing
- scanned documents
- character recognition
- text lines
- free text
- text detection
- sparck jones
- database
- text processing
- text documents
- query expansion
- probabilistic model
- preprocessing
- text analysis
- key concepts
- error correction
- information access
- retrieval effectiveness
- retrieval model
- structured data
- text mining