# Recognizing Cuneiform Signs Using Graph Based Methods

arXiv: https://arxiv.org/abs/1802.05908 · HTML: https://mlsanity.com/paper/1802.05908/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Feb 2018.

## Built on by (most cited first, 14 of 14)

- [Weisfeiler and Leman go Machine Learning: The Story so far](https://mlsanity.com/paper/2112.09992/) (2021)
- [Online Graph Dictionary Learning](https://mlsanity.com/paper/2102.06555/) (2021)
- [Meta-Inductive Node Classification across Graphs](https://mlsanity.com/paper/2105.06725/) (2021)
- [Efficient Approximation of Gromov-Wasserstein Distance Using Importance Sparsification](https://mlsanity.com/paper/2205.13573/) (2022)
- [Ancient Script Image Recognition and Processing: A Review](https://mlsanity.com/paper/2506.19208/) (2025)
- [Recurrent Temporal Revision Graph Networks](https://mlsanity.com/paper/2309.12694/) (2023)
- [DeepScribe: Localization and Classification of Elamite Cuneiform Signs Via Deep Learning](https://mlsanity.com/paper/2306.01268/) (2023)
- [Alignment and Comparison of Directed Networks via Transition Couplings of Random Walks](https://mlsanity.com/paper/2106.07106/) (2021)
- [Shaping History: Advanced Machine Learning Techniques for the Analysis and Dating of Cuneiform Tablets over Three Millennia](https://mlsanity.com/paper/2406.04039/) (2024)
- [Multi-scale Wasserstein Shortest-path Graph Kernels for Graph Classification](https://mlsanity.com/paper/2206.00979/) (2022)
- [Graph Fuzzy System: Concepts, Models and Algorithms](https://mlsanity.com/paper/2210.16730/) (2022)
- [Exploiting Edge Features in Graphs with Fused Network Gromov-Wasserstein Distance](https://mlsanity.com/paper/2309.16604/) (2023)
- [A Recursive Encoding for Cuneiform Signs](https://mlsanity.com/paper/2406.17283/) (2024)
- [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)

The cuneiform script constitutes one of the earliest systems of writing and is realized by wedge-shaped marks on clay tablets. A tremendous number of cuneiform tablets have already been discovered and are incrementally digitalized and made available to automated processing. As reading cuneiform script is still a manual task, we address the real-world application of recognizing cuneiform signs by two graph based methods with complementary runtime characteristics. We present a graph model for cuneiform signs together with a tailored distance measure based on the concept of the graph edit distance. We propose efficient heuristics for its computation and demonstrate its effectiveness in classification tasks experimentally. To this end, the distance measure is used to implement a nearest neighbor classifier leading to a high computational cost for the prediction phase with increasing training set size. In order to overcome this issue, we propose to use CNNs adapted to graphs as an alternative approach shifting the computational cost to the training phase. We demonstrate the practicability of both approaches in an extensive experimental comparison regarding runtime and prediction accuracy. Although currently available annotated real-world data is still limited, we obtain a high accuracy using CNNs, in particular, when the training set is enriched by augmented examples.