Transformer-based HTR for Historical Documents
This work addresses the challenge of digitizing historical manuscripts for archivists and researchers, but it is incremental as it adapts an existing model to a new domain.
The researchers tackled the problem of handwritten text recognition (HTR) for historical documents by applying the TrOCR framework, demonstrating that it outperforms the state-of-the-art Transkribus system without requiring baseline information.
We apply the TrOCR framework to real-world, historical manuscripts and show that TrOCR per se is a strong model, ideal for transfer learning. TrOCR has been trained on English only, but it can adapt to other languages that use the Latin alphabet fairly easily and with little training material. We compare TrOCR against a SOTA HTR framework (Transkribus) and show that it can beat such systems. This finding is essential since Transkribus performs best when it has access to baseline information, which is not needed at all to fine-tune TrOCR.