OCR Nachkorrektur des Royal Society Corpus.
Carsten KlausPeter FankhauserDietrich KlakowPublished in: DHd (2019)
Keyphrases
- optical character recognition
- post processing
- manually annotated
- character recognition
- preprocessing
- recognition errors
- error correction
- artificial intelligence
- open domain
- digital libraries
- text recognition
- document images
- document processing
- human beings
- socio economic
- test set
- supervised machine learning
- character segmentation
- end to end
- hidden markov models
- spanish language