An Indian-led startup company developed an AI system to help businesses and individuals spot counterfeit handbags in the market today.
A team of researchers from the startup Entrupy has developed an AI system that uses algorithms and microscopic camera to analyze and differentiate fake luxury bags from genuine products.
For years, authentic product manufacturers have been losing billions worth of investments due to counterfeit goods. In 2016 alone, the International Trademark Association (INTA) reported that over $460 billion USD worth of fake goods were bought and sold on the market.Say goodbye to fake products with #Entrupy 's AI system and handheld device!Click To Tweet
Further reports suggested that most of the illegal trade transactions were made online. “The internet makes it easy to hide,” said INTA anti-counterfeiting coordinator Tiffany Pho. A study conducted by Red Points, a Barcelona-based brand-protection firm, showed that buying and selling of fake merchandises often occur through AlienExpress, Alibaba’s international marketplace.
Red Points’ research also identified two of the most commonly counterfeited products today: designer sneakers and handbags.
The rampant imitation led many technologists to develop tools that can determine whether a product is fake or real. Such was the case with Entrupy and its AI system that the company claims to be capable of spotting counterfeit handbags.
An AI System to Fight Product Piracy and Imitation
As a solution to the uncontrolled case of luxury handbags’ illegal reproduction, Entrupy created a handheld device equipped with a microscopic camera that will enable anyone to check the authenticity of a luxury merchandise using a smartphone.
The research was spearheaded by the New York University Professor Lakshminarayanan Subramanian and was presented at the KDD Conference Knowledge Discovery and Data Mining in Halifax, Nova Scotia last August 14.
According to the company, the accuracy of their AI system has significantly improved after a year, to better than 98% for 11 of the world’s best luxury brands including Louis Vuitton, Chanel, and Gucci.
“The classification accuracy is more than 98%, and we show how our system works with a cellphone to verify the authenticity of everyday objects,” said Lakshminarayanan Subramanian.
How the AI System Works
The system works by deploying a dataset of three million images across various objects and materials such as fabrics, leather, pills, electronics, toys, and shoes.
Entrupy’s handheld device must be placed directly on the item. One must open the company’s smartphone application and follow the onscreen prompts to take the images. Entrupy claims that its camera can magnify objects 260 times more. Thus, allowing features invisible to human eyes become noticeable.
Some counterfeit signs that the device could uncover include misshapen stamp marks, tiny gaps in leather grain, and paint overruns.
Furthermore, the AI system of Entrupy analyzes the images being fed to it using a machine learning algorithm to determine the authenticity of a product in real-time.
“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,” Subramanian explained.
According to Bloomberg, Entrupy’s database now has tens of millions of photographs from about 30,000 different handbags and wallets. The software learns as clients upload new pictures.
The handheld device which resembles a bulky flashlight with a wireless connection can be rented for an initial fee of $299 USD. Its monthly plans have a $99 USD starting price. In its website, the company said to authenticate the following luxury handbag brands:
- Louis Vuitton
Right now, around 160 businesses which include pawn shops, wholesalers, and online retailers have signed up with Entrupy.
“Today everything is done by humans. For businesses that are growing, that’s not a scalable solution,” says Entrupy co-founder Vidyuth Srinivasan.
“The technology works pretty well on everything except for diamonds and porcelain, because those are refractive and we use optical analysis,” Srinivasan went on to say. “We’ve already tested it on auto parts, phones, chargers, headphones, jackets, shoes, even crude oil.”
In July, Entrupy was able to raise $2.6 million USD from investors led by a venture between Tokyo-based Digital Garage Inc. and Daiwa Securities Group Inc. The money will be used by the company to design a faster and more portable camera and add more brands to Entrupy’s verifiable list.