Riedones3D: a celtic coin dataset for registration and fine-grained clustering
This provides a public dataset and benchmarks to aid numismatic experts in automating coin die clustering, which is incremental as it builds on existing methods by offering new data.
The authors tackled the problem of clustering Celtic coins by their die for numismatic research by introducing a new 3D dataset of 2,070 coin scans, and they proposed benchmarks for registration and clustering with preliminary evaluations.
Clustering coins with respect to their die is an important component of numismatic research and crucial for understanding the economic history of tribes (especially when literary production does not exist, in celtic culture). It is a very hard task that requires a lot of times and expertise. To cluster thousands of coins, automatic methods are becoming necessary. Nevertheless, public datasets for coin die clustering evaluation are too rare, though they are very important for the development of new methods. Therefore, we propose a new 3D dataset of 2 070 scans of coins. With this dataset, we propose two benchmarks, one for point cloud registration, essential for coin die recognition, and a benchmark of coin die clustering. We show how we automatically cluster coins to help experts, and perform a preliminary evaluation for these two tasks. The code of the baseline and the dataset will be publicly available at https://www.npm3d.fr/coins-riedones3d and https://www.chronocarto.eu/spip.php?article84&lang=fr