Supervised OCR Post-Correction of Historical Swedish Texts: What Role Does the OCR System Play?
Dana DannéllsSimon PerssonPublished in: DHN (2020)
Keyphrases
- optical character recognition
- error correction
- character recognition
- recognition errors
- document images
- post processing
- preprocessing
- text recognition
- ocr systems
- scanned documents
- historical manuscripts
- data sets
- document processing
- error detection
- page layout
- natural language generation
- printed documents
- character segmentation
- document image analysis
- text documents
- hidden markov models
- real world