Advancing Post-OCR Correction: A Comparative Study of Synthetic Data
This addresses the challenge of improving OCR accuracy for various languages, including low-resource ones, though it appears incremental as it builds on existing synthetic data methods.
This paper tackles the problem of post-OCR correction by using synthetic data to train models, demonstrating that models like ByT5 can significantly reduce Character Error Rates (CER) without manually annotated data, with their novel glyph similarity method showing advantages over traditional approaches, especially for low-resource languages.
This paper explores the application of synthetic data in the post-OCR domain on multiple fronts by conducting experiments to assess the impact of data volume, augmentation, and synthetic data generation methods on model performance. Furthermore, we introduce a novel algorithm that leverages computer vision feature detection algorithms to calculate glyph similarity for constructing post-OCR synthetic data. Through experiments conducted across a variety of languages, including several low-resource ones, we demonstrate that models like ByT5 can significantly reduce Character Error Rates (CER) without the need for manually annotated data, and our proposed synthetic data generation method shows advantages over traditional methods, particularly in low-resource languages.