A New Approach for Detecting Counterfeit Coins

Researchers at the Centre for Pattern Recognition and Machine Intelligence (CENPARMI) at Concordia University in Montreal, Canada have utilised image-mining techniques and machine learning algorithms to identify flaws in counterfeit coins, enabling greater detection of fakes.

Published in the journal ‘Expert Systems With Applications’, the researchers’ paper details the use of image technology to scan both genuine and counterfeit coins to look for anomalies that may be two- or three-dimensional, such as letters or portraits featured on the coin ¹.

The paper’s lead author, CENPARMI postdoctoral fellow Maryam Sharifi Rad, noted that the framework is not only about safeguarding economy and resources but also ‘pushing the boundaries of technology and improving security’.

The researchers’ framework is built around fuzzy association rules mining, utilising artificial intelligence to find similar patterns that are ‘fuzzy’, ie. unclear enough to be exact copies. While numerous studies have explored various approaches for mining images and extracting strong association rules, there is still a critical gap in leveraging fuzzy associative classifiers for counterfeit coin detection, using coin image datasets.