Post OCR Correction of Swedish Patent Text - The Difference between Reading Tongue 'Lästunga' and Security Tab 'Låstunga'.
Linda AnderssonHelena RastasAndreas RauberPublished in: IRFC (2014)
Keyphrases
- free text
- text recognition
- information retrieval
- error correction
- document processing
- printed documents
- optical character recognition
- document images
- ocr systems
- document analysis
- text extraction
- reading comprehension
- page layout
- text retrieval
- network security
- printed text
- security policies
- database
- scene text
- post processing
- text regions
- keywords
- text mining
- scanned documents
- intrusion detection
- handwriting recognition
- security requirements
- statistical databases
- motion analysis
- security mechanisms
- text lines
- information security
- preprocessing
- active contour model
- information extraction
- access control
- recognition errors
- character recognition
- natural language processing
- scanned images
- information retrieval systems
- security issues
- intellectual property
- document collections