# DeepScribe: Localization and Classification of Elamite Cuneiform Signs Via Deep Learning

arXiv: https://arxiv.org/abs/2306.01268 · HTML: https://mlsanity.com/paper/2306.01268/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 77 references that are in the map.
- First posted on arXiv 2 Jun 2023.

## Builds on (most cited first, 17 of 17)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [Revisiting Unreasonable Effectiveness of Data in Deep Learning Era](https://mlsanity.com/paper/1707.02968/) (2017)
- [A review of deep learning in medical imaging: Imaging traits, technology trends, case studies with progress highlights, and future promises](https://mlsanity.com/paper/2008.09104/) (2020)
- [Learning Visual Features from Large Weakly Supervised Data](https://mlsanity.com/paper/1511.02251/) (2015)
- [Joint Line Segmentation and Transcription for End-to-End Handwritten Paragraph Recognition](https://mlsanity.com/paper/1604.08352/) (2016)
- [Restoring ancient text using deep learning: a case study on Greek epigraphy](https://mlsanity.com/paper/1910.06262/) (2019)
- [Recognizing Cuneiform Signs Using Graph Based Methods](https://mlsanity.com/paper/1802.05908/) (2018)
- [A Computationally Efficient Pipeline Approach to Full Page Offline Handwritten Text Recognition](https://mlsanity.com/paper/1910.00663/) (2019)
- [Deciphering Undersegmented Ancient Scripts Using Phonetic Prior](https://mlsanity.com/paper/2010.11054/) (2020)
- [Neural Decipherment via Minimum-Cost Flow: from Ugaritic to Linear B](https://mlsanity.com/paper/1906.06718/) (2019)
- [Chinese Text in the Wild](https://mlsanity.com/paper/1803.00085/) (2018)

## Built on by (most cited first, 4 of 4)

- [CNN based Cuneiform Sign Detection Learned from Annotated 3D Renderings and Mapped Photographs with Illumination Augmentation](https://mlsanity.com/paper/2308.11277/) (2023)
- [Deep Aramaic: Towards a Synthetic Data Paradigm Enabling Machine Learning in Epigraphy](https://mlsanity.com/paper/2310.07310/) (2023)
- [Signs of the Past, Patterns of the Present: On the Automatic Classification of Old Babylonian Cuneiform Signs](https://mlsanity.com/paper/2507.13959/) (2025)
- [Zero-Shot SAM2 Segmentation and Vision Transformer-Based Recognition of Elamite Cuneiform Symbols from Degraded Tablet Images](https://mlsanity.com/paper/2608.18544/) (2026)

## Abstract (arXiv)

Twenty-five hundred years ago, the paperwork of the Achaemenid Empire was recorded on clay tablets. In 1933, archaeologists from the University of Chicago's Oriental Institute (OI) found tens of thousands of these tablets and fragments during the excavation of Persepolis. Many of these tablets have been painstakingly photographed and annotated by expert cuneiformists, and now provide a rich dataset consisting of over 5,000 annotated tablet images and 100,000 cuneiform sign bounding boxes. We leverage this dataset to develop DeepScribe, a modular computer vision pipeline capable of localizing cuneiform signs and providing suggestions for the identity of each sign. We investigate the difficulty of learning subtasks relevant to cuneiform tablet transcription on ground-truth data, finding that a RetinaNet object detector can achieve a localization mAP of 0.78 and a ResNet classifier can achieve a top-5 sign classification accuracy of 0.89. The end-to-end pipeline achieves a top-5 classification accuracy of 0.80. As part of the classification module, DeepScribe groups cuneiform signs into morphological clusters. We consider how this automatic clustering approach differs from the organization of standard, printed sign lists and what we may learn from it. These components, trained individually, are sufficient to produce a system that can analyze photos of cuneiform tablets from the Achaemenid period and provide useful transliteration suggestions to researchers. We evaluate the model's end-to-end performance on locating and classifying signs, providing a roadmap to a linguistically-aware transliteration system, then consider the model's potential utility when applied to other periods of cuneiform writing.