# Deep Aramaic: Towards a Synthetic Data Paradigm Enabling Machine Learning in Epigraphy

arXiv: https://arxiv.org/abs/2310.07310 · HTML: https://mlsanity.com/paper/2310.07310/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 102 references that are in the map.
- First posted on arXiv 11 Oct 2023.

## Builds on (most cited first, 23 of 23)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [Identity Mappings in Deep Residual Networks](https://mlsanity.com/paper/1603.05027/) (2016)
- [Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World](https://mlsanity.com/paper/1703.06907/) (2017)
- [Synthetic Data for Text Localisation in Natural Images](https://mlsanity.com/paper/1604.06646/) (2016)
- [Training Deep Networks with Synthetic Data: Bridging the Reality Gap by Domain Randomization](https://mlsanity.com/paper/1804.06516/) (2018)
- [Deep Object Pose Estimation for Semantic Robotic Grasping of Household Objects](https://mlsanity.com/paper/1809.10790/) (2018)
- [Synthetic Data and Artificial Neural Networks for Natural Scene Text Recognition](https://mlsanity.com/paper/1406.2227/) (2014)
- [Driving in the Matrix: Can Virtual Worlds Replace Human-Generated Annotations for Real World Tasks?](https://mlsanity.com/paper/1610.01983/) (2016)
- [Synthetic Data for Deep Learning](https://mlsanity.com/paper/1909.11512/) (2019)
- [How much real data do we actually need: Analyzing object detection performance using synthetic and real data](https://mlsanity.com/paper/1907.07061/) (2019)
- [A Scalable Handwritten Text Recognition System](https://mlsanity.com/paper/1904.09150/) (2019)
- [Restoring ancient text using deep learning: a case study on Greek epigraphy](https://mlsanity.com/paper/1910.06262/) (2019)
- [AGTGAN: Unpaired Image Translation for Photographic Ancient Character Generation](https://mlsanity.com/paper/2303.07012/) (2023)
- [Restoration of Fragmentary Babylonian Texts Using Recurrent Neural Networks](https://mlsanity.com/paper/2003.01912/) (2020)
- [Artificial intelligence based writer identification generates new evidence for the unknown scribes of the Dead Sea Scrolls exemplified by the Great Isaiah Scroll (1QIsaa)](https://mlsanity.com/paper/2010.14476/) (2020)
- [Filling the Gaps in Ancient Akkadian Texts: A Masked Language Modelling Approach](https://mlsanity.com/paper/2109.04513/) (2021)
- [Synthetic 3D Data Generation Pipeline for Geometric Deep Learning in Architecture](https://mlsanity.com/paper/2104.12564/) (2021)
- [Generating Synthetic Handwritten Historical Documents With OCR Constrained GANs](https://mlsanity.com/paper/2103.08236/) (2021)
- [Reducing the Amount of Real World Data for Object Detector Training with Synthetic Data](https://mlsanity.com/paper/2202.00632/) (2022)
- [DeepScribe: Localization and Classification of Elamite Cuneiform Signs Via Deep Learning](https://mlsanity.com/paper/2306.01268/) (2023)
- [Learning from scarce information: using synthetic data to classify Roman fine ware pottery](https://mlsanity.com/paper/2107.01401/) (2021)
- [Towards Knowledge Discovery from the Vatican Secret Archives. In Codice Ratio -- Episode 1: Machine Transcription of the Manuscripts](https://mlsanity.com/paper/1803.03200/) (2018)

## Built on by (most cited first, 2 of 2)

- [Zero-Shot SAM2 Segmentation and Vision Transformer-Based Recognition of Elamite Cuneiform Symbols from Degraded Tablet Images](https://mlsanity.com/paper/2608.18544/) (2026)
- [DDVR-Net: Degradation-Aware Decoupling and Visibility-Guided Restoration for Historical Document Recognition](https://mlsanity.com/paper/2610.16956/) (2026)

## Abstract (arXiv)

Epigraphy increasingly turns to modern artificial intelligence (AI) technologies such as machine learning (ML) for extracting insights from ancient inscriptions. However, scarce labeled data for training ML algorithms severely limits current techniques, especially for ancient scripts like Old Aramaic. Our research pioneers an innovative methodology for generating synthetic training data tailored to Old Aramaic letters. Our pipeline synthesizes photo-realistic Aramaic letter datasets, incorporating textural features, lighting, damage, and augmentations to mimic real-world inscription diversity. Despite minimal real examples, we engineer a dataset of 250,000 training and 25,000 validation images covering the 22 letter classes in the Aramaic alphabet. This comprehensive corpus provides a robust volume of data for training a residual neural network (ResNet) to classify highly degraded Aramaic letters. The ResNet model demonstrates high accuracy in classifying real images from the 8th century BCE Hadad statue inscription. Additional experiments validate performance on varying materials and styles, proving effective generalization. Our results validate the model's capabilities in handling diverse real-world scenarios, proving the viability of our synthetic data approach and avoiding the dependence on scarce training data that has constrained epigraphic analysis. Our innovative framework elevates interpretation accuracy on damaged inscriptions, thus enhancing knowledge extraction from these historical resources.