University of Southampton OCS (beta), CAA 2012

Font Size: 
Automatic coin classification and identification
Reinhold Huber-Mörk, Michael Nölle, Michael Rubik, Michael Hödlmoser, Martin Kampel, Sebastian Zambanini

Last modified: 2011-12-17


We investigate coin image recognition and classification in a setting with a large number of coin classes as well as recognition and identification of individual coins with high similarity. Real-world image data sets were obtained for modern and ancient coins.. The considered classification task is the discrimination of modern coins into several hundreds of different classes. Identification is investigated for hand-made ancient coins. Intra-class variance due to wear and abrasion vs. small inter-class variance makes the classification of modern coins challenging. For ancient coins the intraclass-variance makes the identification task possible, as the appearance of individual hand-struck coins is unique. Modern coins are acquired by a machine vision system for coin sorting. For ancient coins the setting is more general, images acquired by scanner and camera devices are considered. We will discuss image processing methods for coin images and present results for real-world data sets.


computer vision