A simple numeric algorithm for ancient coin dies identification
Luca Lista

TL;DR
This paper introduces a straightforward computer algorithm to identify coins from the same die using image analysis, providing a quantitative tool to assist visual inspection of pre-modern coins from auction images.
Contribution
The paper presents a simple, practical algorithm for coin die identification that does not require complex image processing or high-quality images, aiding numismatic analysis.
Findings
Effective in identifying coins from the same die
Applicable to images from auction websites or catalogs
Provides a quantitative measure of similarity
Abstract
A simple computer-based algorithm has been developed to identify pre-modern coins minted from the same dies, intending mainly coins minted by hand-made dies designed to be applicable to images taken from auction websites or catalogs. Though the method is not intended to perform a complete automatic classification, which would require more complex and intensive algorithms accessible to experts of computer vision its simplicity of use and lack of specific requirement about the quality of pictures can provide help and complementary information to the visual inspection, adding quantitative measurements of the "distance" between pairs of different coins. The distance metric is based on a number of pre-defined reference points that mark key features of the coin to identify the set of coins they have been minted from.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsCurrency Recognition and Detection · Image Processing and 3D Reconstruction · Cultural Heritage Materials Analysis
