# FP-THD: Full page transcription of historical documents

arXiv: https://arxiv.org/abs/2601.17040 · HTML: https://mlsanity.com/paper/2601.17040/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 47 references that are in the map.
- First posted on arXiv 20 Jan 2026.

## Builds on (most cited first, 14 of 14)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [DE-GAN: A Conditional Generative Adversarial Network for Document Enhancement](https://mlsanity.com/paper/2010.08764/) (2020)
- [A Two-Stage Method for Text Line Detection in Historical Documents](https://mlsanity.com/paper/1802.03345/) (2018)
- [HTR-VT: Handwritten Text Recognition with Vision Transformer](https://mlsanity.com/paper/2409.08573/) (2024)
- [Joint Layout Analysis, Character Detection and Recognition for Historical Document Digitization](https://mlsanity.com/paper/2007.06890/) (2020)
- [Page Layout Analysis System for Unconstrained Historic Documents](https://mlsanity.com/paper/2102.11838/) (2021)
- [The LAM Dataset: A Novel Benchmark for Line-Level Handwritten Text Recognition](https://mlsanity.com/paper/2208.07682/) (2022)
- [Predicting the Original Appearance of Damaged Historical Documents](https://mlsanity.com/paper/2412.11634/) (2024)
- [TS-Net: OCR Trained to Switch Between Text Transcription Styles](https://mlsanity.com/paper/2103.05489/) (2021)
- [Normalized vs Diplomatic Annotation: A Case Study of Automatic Information Extraction from Handwritten Uruguayan Birth Certificates](https://mlsanity.com/paper/2507.08636/) (2025)
- [Fine-tuning Handwriting Recognition systems with Temporal Dropout](https://mlsanity.com/paper/2102.00511/) (2021)
- [SDT-DCSCN for Simultaneous Super-Resolution and Deblurring of Text Images](https://mlsanity.com/paper/2201.05865/) (2022)
- [Artificial Intelligence in archival and historical scholarship workflow: HTS and ChatGPT](https://mlsanity.com/paper/2308.02044/) (2023)

## Abstract (arXiv)

The transcription of historical documents written in Latin in XV and XVI centuries has special challenges as it must maintain the characters and special symbols that have distinct meanings to ensure that historical texts retain their original style and significance. This work proposes a pipeline for the transcription of historical documents preserving these special features. We propose to extend an existing text line recognition method with a layout analysis model. We analyze historical text images using a layout analysis model to extract text lines, which are then processed by an OCR model to generate a fully digitized page. We showed that our pipeline facilitates the processing of the page and produces an efficient result. We evaluated our approach on multiple datasets and demonstrate that the masked autoencoder effectively processes different types of text, including handwritten, printed and multi-language.