Advancing Post-OCR Correction: A Comparative Study of Synthetic Data.
Shuhao GuanDerek GreenePublished in: ACL (Findings) (2024)
Keyphrases
- synthetic data
- error correction
- optical character recognition
- document images
- real world
- character recognition
- post processing
- data sets
- error detection
- real image data
- recognition errors
- text recognition
- comparative study
- printed documents
- website
- image processing
- artificial intelligence
- database
- artificial neural networks
- video sequences
- mri data
- document image analysis
- document processing
- character segmentation
- information retrieval
- ocr systems
- databases