Data Generation for Post-OCR correction of Cyrillic handwriting.
Evgenii DavydkinAleksandr MarkelovEgor IuldashevAnton DudkinIvan KrivorotovPublished in: CoRR (2023)
Keyphrases
- data generation
- character recognition
- handwriting recognition
- error correction
- optical character recognition
- printed documents
- scanned images
- active learning
- document images
- data streams
- printed text
- high throughput
- machine vision
- handwritten documents
- streaming data
- co training
- chinese characters
- document analysis
- word recognition
- labeled data
- data mining
- data sets
- document image analysis
- concept drift
- viewpoint
- data analysis