Automatic clustering of Celtic coins based on 3D point cloud pattern\n analysis

2020/05/12 by Sofiane Horache, Horache, Sofiane, Deschaud, Jean-Emmanuel +3
Computer Science · Arts and Humanities · #Currency Recognition and Detection #Image Processing and 3D Reconstruction #Cultural Heritage Materials Analysis

paper · pdf · doi:10.48550/arxiv.2005.05705

Abstract

The recognition and clustering of coins which have been struck by the same\ndie is of interest for archeological studies. Nowadays, this work can only be\nperformed by experts and is very tedious. In this paper, we propose a method to\nautomatically cluster dies, based on 3D scans of coins. It is based on three\nsteps: registration, comparison and graph-based clustering. Experimental\nresults on 90 coins coming from a Celtic treasury from the II-Ith century BC\nshow a clustering quality equivalent to expert's work.\n

Related

• Riedones3D: a celtic coin dataset for registration and fine-grained clustering
• Supporting a Celtic coin die study with image matching and hierarchical clustering for creating a social networks analysis
• Unsupervised Statistical Learning for Die Analysis in Ancient Numismatics
• Automatic Die Studies for Ancient Numismatics
• A High-Accuracy SSIM-based Scoring System for Coin Die Link Identification