# Generating Synthetic Handwritten Historical Documents With OCR Constrained GANs

arXiv: https://arxiv.org/abs/2103.08236 · HTML: https://mlsanity.com/paper/2103.08236/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 31 references that are in the map.
- First posted on arXiv 15 Mar 2021.

## Builds on (most cited first, 12 of 12)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Unsupervised Cross-Domain Image Generation](https://mlsanity.com/paper/1611.02200/) (2016)
- [SteganoGAN: High Capacity Image Steganography with GANs](https://mlsanity.com/paper/1901.03892/) (2019)
- [GANwriting: Content-Conditioned Generation of Styled Handwritten Word Images](https://mlsanity.com/paper/2003.02567/) (2020)
- [CycleGAN, a Master of Steganography](https://mlsanity.com/paper/1712.02950/) (2017)
- [Scan, Attend and Read: End-to-End Handwritten Paragraph Recognition with MDLSTM Attention](https://mlsanity.com/paper/1604.03286/) (2016)
- [A Comprehensive Study of ImageNet Pre-Training for Historical Document Image Analysis](https://mlsanity.com/paper/1905.09113/) (2019)
- [Labeling, Cutting, Grouping: an Efficient Text Line Segmentation Method for Medieval Manuscripts](https://mlsanity.com/paper/1906.11894/) (2019)
- [DocEmul: a Toolkit to Generate Structured Historical Documents](https://mlsanity.com/paper/1710.03474/) (2017)
- [A Pitfall of Unsupervised Pre-Training](https://mlsanity.com/paper/1712.01655/) (2017)
- [Powers of layers for image-to-image translation](https://mlsanity.com/paper/2008.05763/) (2020)

## Built on by (most cited first, 5 of 5)

- [WordStylist: Styled Verbatim Handwritten Text Generation with Latent Diffusion Models](https://mlsanity.com/paper/2303.16576/) (2023)
- [VATr++: Choose Your Words Wisely for Handwritten Text Generation](https://mlsanity.com/paper/2402.10798/) (2024)
- [Deep Aramaic: Towards a Synthetic Data Paradigm Enabling Machine Learning in Epigraphy](https://mlsanity.com/paper/2310.07310/) (2023)
- [DIVA-DAF: A Deep Learning Framework for Historical Document Image Analysis](https://mlsanity.com/paper/2201.08295/) (2022)
- [UniLipi: A Unified Multi-Script OCR for Historical Indic Manuscripts](https://mlsanity.com/paper/2608.28195/) (2026)

## Abstract (arXiv)

We present a framework to generate synthetic historical documents with precise ground truth using nothing more than a collection of unlabeled historical images. Obtaining large labeled datasets is often the limiting factor to effectively use supervised deep learning methods for Document Image Analysis (DIA). Prior approaches towards synthetic data generation either require expertise or result in poor accuracy in the synthetic documents. To achieve high precision transformations without requiring expertise, we tackle the problem in two steps. First, we create template documents with user-specified content and structure. Second, we transfer the style of a collection of unlabeled historical images to these template documents while preserving their text and layout. We evaluate the use of our synthetic historical documents in a pre-training setting and find that we outperform the baselines (randomly initialized and pre-trained). Additionally, with visual examples, we demonstrate a high-quality synthesis that makes it possible to generate large labeled historical document datasets with precise ground truth.