# Unsupervised Statistical Learning for Die Analysis in Ancient Numismatics

arXiv: https://arxiv.org/abs/2112.00290 · HTML: https://mlsanity.com/paper/2112.00290/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 65 references that are in the map.
- First posted on arXiv 1 Dec 2021.

## Builds on (most cited first, 10 of 10)

- [Flexible Models for Microclustering with Application to Entity Resolution](https://mlsanity.com/paper/1610.09780/) (2016)
- [Gaussian Process Landmarking on Manifolds](https://mlsanity.com/paper/1802.03479/) (2018)
- [Search Algorithms and Loss Functions for Bayesian Clustering](https://mlsanity.com/paper/2105.04451/) (2021)
- [Random Partition Models for Microclustering Tasks](https://mlsanity.com/paper/2004.02008/) (2020)
- [Bayesian Distance Clustering](https://mlsanity.com/paper/1810.08537/) (2018)
- [Riedones3D: a celtic coin dataset for registration and fine-grained clustering](https://mlsanity.com/paper/2109.15033/) (2021)
- [Deep Ancient Roman Republican Coin Classification via Feature Fusion and Attention](https://mlsanity.com/paper/1908.09428/) (2019)
- [Cohesion and Repulsion in Bayesian Distance Clustering](https://mlsanity.com/paper/2107.05414/) (2021)
- [Discovering Characteristic Landmarks on Ancient Coins using Convolutional Networks](https://mlsanity.com/paper/1506.09174/) (2015)
- [Variational Auto Encoder Gradient Clustering](https://mlsanity.com/paper/2105.06246/) (2021)

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

- [Artificial Intelligence Generated Coins for Size Comparison](https://mlsanity.com/paper/2301.04751/) (2023)
- [Automatic Die Studies for Ancient Numismatics](https://mlsanity.com/paper/2407.20876/) (2024)

## Abstract (arXiv)

Die analysis is an essential numismatic method, and an important tool of ancient economic history. Yet, manual die studies are too labor-intensive to comprehensively study large coinages such as those of the Roman Empire. We address this problem by proposing a model for unsupervised computational die analysis, which can reduce the time investment necessary for large-scale die studies by several orders of magnitude, in many cases from years to weeks. From a computer vision viewpoint, die studies present a challenging unsupervised clustering problem, because they involve an unknown and large number of highly similar semantic classes of imbalanced sizes. We address these issues through determining dissimilarities between coin faces derived from specifically devised Gaussian process-based keypoint features in a Bayesian distance clustering framework. The efficacy of our method is demonstrated through an analysis of 1135 Roman silver coins struck between 64-66 C.E..