From Testing Lipstick to Spotting Terrorists

Technology from beauty industry does a beautiful job of spotting bad guys

2 min read
From Testing Lipstick to Spotting Terrorists


Jean-Marc Robin, CEO of startup Vesalis from Clermont-Ferrand, France, got into the beauty industry, he says, “because I love women.” (That phrase in quotes should be read with a French accent if at all possible.) He seems somewhat surprised to find his company’s facial recognition technology, built to help department stores sell makeup, drawing interest from governments, French and otherwise. But he does love that they love the technology and its possibilities.

Talking with Robin during his visit to Palo Alto, Calif., last week, he definitely seemed like a man tugged in two directions. While he was happy to talk about the successes of the technology in security tests, he kept bringing the conversation back to its applications in department stores, guiding women to selections of hair color and makeup.

The company, started in 2005, has eight patents for its facial recognition technology. While it mainly had in mind department store kiosks, where shoppers use it to virtually test makeup applied to photographs taken of themselves, that’s not what has the security folks excited. It’s the video streams that, in the envisioned department store application, would come from existing security cameras that has them intrigued. In department stores, Vesalis’ software compares these relatively low quality images against a database of existing customers: When the system spots a known customer coming into the store, it sends an alert to an iPad carried by a salesperson. The salesperson can then quickly look at the customer’s picture, previous order history, and other information, greet the customer by name and perhaps suggest sale or other items she might be interested in.

This fast image recognition from low-quality video, in turns out, is just what security companies dream of, to compare people against a database of known “people of concern.” The French government invested €2 million in the company in 2009, and this past October, Vesalis tested its technology during a soccer game at the Parc des Princes, the largest soccer stadium in France. The system checked 20 000 people every 20 minutes against a database of 500 problem individuals and had an accuracy rate of 98 percent; competitive technology, said Michael Vannier, Vice President of U.S. Sales, has had an accuracy rate of 61 percent in similar tests. The company expects its technology, in the future, to be used in counterterrorism, border control, ATM access, and a variety of security applications. And, Robin hopes, at a few makeup counters.

The Conversation (0)

The Future of Deep Learning Is Photonic

Computing with light could slash the energy needs of neural networks

10 min read
Image of a computer rendering.

This computer rendering depicts the pattern on a photonic chip that the author and his colleagues have devised for performing neural-network calculations using light.

Alexander Sludds

Think of the many tasks to which computers are being applied that in the not-so-distant past required human intuition. Computers routinely identify objects in images, transcribe speech, translate between languages, diagnose medical conditions, play complex games, and drive cars.

The technique that has empowered these stunning developments is called deep learning, a term that refers to mathematical models known as artificial neural networks. Deep learning is a subfield of machine learning, a branch of computer science based on fitting complex models to data.

Keep Reading ↓Show less