A team of researchers has developed a new mechanism that uses a machine-learning system to detect counterfeit products.
This research was led by New York University Professor Lakshimarayanan Subramanian and will be presented at the annual KDD Conference on Knowledge Discovery and Data Mining in Halifax, Nova Scotia.
"The underlying principle of our system stems from the idea that microscopic characteristics in a genuine product or a class of products—corresponding to the same larger product line—exhibit inherent similarities that can be used to distinguish these products from their corresponding counterfeit versions," explains Subramanian, a professor at NYU's Courant Institute of Mathematical Sciences.
Counterfeit goods are a huge problem with high-value objects or products. Some reports say that counterfeit trafficking represents 7 percent of the world’s trade.
Other counterfeit-detection methods are invasive and run the risk of damaging the products when they are examined.
This new method, called the Entrupy method, is a non-intrusive solution to easily distinguishing if a product is real or fake. The process involves deploying a data set of three million images across objects and materials like leather, pills, electronics, toys and shoes.
"The classification accuracy is more than 98 percent, and we show how our system works with a cell phone to verify the authenticity of everyday objects," notes Subramanian.
To date, Entrupy has authenticated $14 million worth of goods.