Identification of ancient coins based on fusion of shape and local features

We present a vision-based approach to ancient coins’ identification. The approach is a two-stage procedure. In the first stage an invariant shape description of the coin edge is computed and matching based on shape is performed. The second stage uses preselection by the first stage in order to refin...

Full description

Saved in:
Bibliographic Details
Published in:Machine vision and applications 2011-11, Vol.22 (6), p.983-994
Main Authors: Huber-Mörk, Reinhold, Zambanini, Sebastian, Zaharieva, Maia, Kampel, Martin
Format: Article
Language:English
Subjects:
Bayesian analysis
Coins
Communications Engineering
Computer Science
Image Processing and Computer Vision
Matching
Networks
Original Paper
Pattern Recognition
Vision systems
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We present a vision-based approach to ancient coins’ identification. The approach is a two-stage procedure. In the first stage an invariant shape description of the coin edge is computed and matching based on shape is performed. The second stage uses preselection by the first stage in order to refine the matching using local descriptors. Results for different descriptors and coin sides are combined using naive Bayesian fusion. Identification rates on a comprehensive data set of 2400 images of ancient coins are on the order of magnitude of 99%.
ISSN:0932-8092
1432-1769
DOI:10.1007/s00138-010-0283-y