1. Identification of ancient coins based on fusion of shape and local features.
- Author
-
Huber-Mörk, Reinhold, Zambanini, Sebastian, Zaharieva, Maia, and Kampel, Martin
- Subjects
- *
ANCIENT coins , *BIOMETRIC identification , *IMAGE processing , *BAYESIAN analysis , *COMPUTER-aided design - Abstract
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%. [ABSTRACT FROM AUTHOR]
- Published
- 2011
- Full Text
- View/download PDF