Aug 21 2017

Seems Legit!

Dan

Blog post image

A team from New York University led by Professor Lakshminarayanan Subramanian developed a new way to use machine-learning algorithms to tell original and counterfeit products apart. This novel approach to using machine learning was presented last Aug. 14 at the annual KDD Conference on Knowledge Discovery in Halifax, Nova Scotia, Canada.


“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.


The presentation featured the system which is now commercialized by Entrupy Inc, a New York University startup founded by Ashlesh Sharma, a doctoral graduate from the Courant Institute, Vidyuth Srinivasan, and Prof. Subramanian.


And the benefits of such an invention are obvious. Fake goods are indeed a massive global problem which targets nearly all high-valued products. Some statistical reports on international crime say that counterfeit products represent some 7% of the global trade today.


If you are familiar with intellectual property issues, you may be aware that other counterfeit-detection methods already exist. But those are invasive and risk damaging the product under examination. The Entrupy method, however, provides a fast and non-intrusive solution that distinguishes the real from the fake versions of a product. It works by deploying a dataset of millions of images of various objects and materials that have typical surface patterns. They range from fabrics to leather, pills, food items, toys and shoes. The system is said to have an accuracy index of over 98%. It has been ported as a smartphone app for easier demonstration. To date, Entrupy, which recently received $2.6 million in funding from a team of investors, has authenticated $14 million worth of goods.


Here at Tenex Developers, we are always excited to learn the many clever solutions that researchers come up with on a regular basis. Plus, we create our own solutions whenever a challenge is presented by one of our clients. The accelerating pace of discovery is something we all need to learn to adapt, and we excel at creating adaptive technologies. And we are ready to help you be the next success story. Give us a call at 1-833-TENEX10 or send us an email and we will show you how to stay ahead of the curve. The future is now.