ICDAR2017 Competition on Post-OCR Text Correction.
Guillaume ChironAntoine DoucetMickaël CoustatyJean-Philippe MoreuxPublished in: ICDAR (2017)
Keyphrases
- text lines
- text detection
- scanned documents
- optical character recognition
- text recognition
- document images
- printed documents
- error correction
- document processing
- text regions
- ocr systems
- text extraction
- information retrieval
- text retrieval
- database
- text processing
- document analysis
- connected components
- post processing
- textual data
- textual information
- printed text
- keywords
- structural features
- page layout
- character recognition
- text mining
- preprocessing
- street view
- historical manuscripts
- urban scenes
- handwriting recognition
- text analysis
- information extraction
- real world