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

05/12/2020
by   Sofiane Horache, et al.
0

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

READ FULL TEXT

page 1

page 3

page 4

page 5

page 8

research
09/30/2021

Riedones3D: a celtic coin dataset for registration and fine-grained clustering

Clustering coins with respect to their die is an important component of ...
research
03/29/2023

Topological Point Cloud Clustering

We present Topological Point Cloud Clustering (TPCC), a new method to cl...
research
08/15/2022

Global Consistent Point Cloud Registration Based on Lie-algebraic Cohomology

We present a novel, effective method for global point cloud registration...
research
10/14/2017

K-means clustering for efficient and robust registration of multi-view point sets

Efficiency and robustness are the important performance for the registra...
research
12/17/2004

Clustering Techniques for Marbles Classification

Automatic marbles classification based on their visual appearance is an ...
research
05/10/2020

Comparison and Benchmark of Graph Clustering Algorithms

Graph clustering is widely used in analysis of biological networks, soci...
research
05/10/2012

Modularity-Based Clustering for Network-Constrained Trajectories

We present a novel clustering approach for moving object trajectories th...

Please sign up or login with your details

Forgot password? Click here to reset