Novel Approach to Detect Counterfeit Coins

Researchers at the Centre for Pattern Recognition and Machine Intelligence (CENPARMI), at Concordia University, Canada, have developed a novel framework that uses image-mining techniques and machine learning algorithms to identify flaws in counterfeit coins.

According to Ching Suen, a professor in the university’s Department of Computer Science and Software Engineering, and paper supervising author, the researchers used image technology to scan both genuine and counterfeit coins to look for 2D or 3D anomalies, such as in the letters or portraits on the coins.

The researchers’ framework is built around fuzzy association rules mining. This approach uses artificial intelligence to find similar patterns that are ‘fuzzy’, ie. not clear enough to be exact copies. However, the framework will eventually arrive at a specific range of results where positive matches can be confidently identified.

The method begins by examining coins suspected of being counterfeit using state-of-the-art scanners. Law enforcement agencies provide the coins. The scanned images are then segmented into regions of interest, which consist of collections of localised coherent regions referred to as ‘blobs’. These blobs are recognised based on visual similarity and composition, which provide relevant features the researchers can extract. Blobs are like clues that help the researchers figure out what is happening in the scanned images.