Physical beauty is subjective and often difficult to define. But for the robot jury of Beauty.AI, an online competition billed as "the first international beauty contest judged by artificial intelligence," beauty is calculated by a set of complex algorithms that measure parameters like participants' facial symmetry and skin quality.
The contest, launched in December, is an experiment by Youth Laboratories, an international team of data scientists and biogerontologists interested in developing anti-aging technologies. Its aim is to test and demonstrate how computers can learn to assess human attractiveness. The robot jury uses algorithms to analyze and rate participants' selfies submitted through the Beauty.AI app.
"We wanted to create a platform for impartial analysis of human faces, of human beauty," Anastasia Georgievskaya, project manager of Beauty.AI and general manager of Youth Laboratories, says.
Teaching computers about aesthetics involves designing sophisticated algorithms to recognize and measure features like wrinkles, face proportions, blemishes and skin colour. And the beauty industry is rapidly embracing these high-tech tools to respond to consumers' demand for products that suit their individual tastes and attributes.
Companies like Sephora and Avon, for instance, are using face simulation technology to provide apps that allow customers to virtually try on and shop for lipsticks and eye shadows using their mobile devices. Skincare producers are using similar technologies to track and predict the effects of serums and creams on various skin types. And brands like L'Oréal's Lancôme are using facial analysis to read consumers' skin tones to create personalized foundations.
"The more we're able to use these tools like augmented reality [and] artificial intelligence to provide new consumer experiences, the more we can move to customizing and personalizing products for every consumer around the world, no matter what their skin tone is, no matter where they live, no matter who they are," says Guive Balooch, global vice-president of L'Oréal's technology incubator.
Balooch was tasked with starting up the company's tech research hub four years ago, with a mandate to predict and invent solutions to how consumers would choose and use products in the future. Among its innovations, his team has come up with the Makeup Genius app, a virtual mirror that allows customers to try on products on a mobile screen, and a device called My UV Patch, a sticker sensor that users wear on their skin, which informs them through an app how much UV exposure they get.
These tools may seem easy enough to use, but their simplicity belies the work that goes on behind the scenes. To create the Makeup Genius app, for example, Balooch says the developers sought expertise from the animation industry to enable users to see themselves move onscreen in real time. The developers also brought in hundreds of consumers with different skin tones to test real products in the lab, and they tested the app on some 100,000 images in more than 40 lighting conditions, to ensure the colours of makeup products appeared the same in real life as they did onscreen, Balooch says.
Lancôme's new Le Teint Particulier, meanwhile, offers a glimpse of how high-tech tools can be used to tailor cosmetics, Balooch says. The foundation product, which is currently available only in Nordstrom stores in Seattle and Torrance, Calif., involves scanning customers' faces with a device that can read their skin tones. A machine then recreates that skin tone from a selection of 20,000 pigments to formate a customized product.
Whether the goal is to boost brand awareness or to sell products online, many beauty companies see artificial intelligence and augmented reality technologies as a way of engaging customers who increasingly use their mobile devices to shop, says Jennifer Tidy, vice-president of partnerships at ModiFace.
The Toronto-based face simulation technology company has created hundreds of apps for more than 60 beauty and skincare brands around the world, Tidy says. Its clients have included Sephora, Avon, Botox and Juvederm. One of ModiFace's newest creations is an artificial intelligence beauty advisor, a robot that offers lipstick recommendations over Facebook chat.
These kinds of technologies expose consumers to products that they might not otherwise have been aware of, Tidy says.
"There's definitely an educational factor. There's an entertainment factor. But at the end of the day, it's really helping with the need for instant gratification [of] consumers when they're shopping and playing around with products," she says.
Back at Beauty.AI, Georgievskaya says public reaction to the robot-judged beauty competition has been mixed. While many have expressed interest, she says, "Some of them were angry, like how are you to judge beauty with algorithms when it's such a complicated thing?"
Georgievskaya says she understands it's complicated, which is why she anticipates the robot jury will become increasingly sophisticated as more people provide images and more algorithms are created. The contest is also open to computer developers to pitch their facial-analysis algorithms.
Ultimately, the contest is less about the human competitors than it is about the technology. Although an initial 10 winners were announced in February out of 5,000 selfie submissions, photos and details about them were not widely released. (The winning photos Georgievskaya shared with the Globe reveal attractive men and women from the contest's five age categories, ranging from their 20s to 60s. To this human eye, theirs is more of a boy– or girl-next-door type of beauty than stunning supermodel good looks.) Beauty.AI is now accepting submissions for its second contest, ending in August.
Teaching computers to recognize beauty may also train them to identify health conditions, Georgievskaya explains. Youth Laboratories is also working on ways to identify biomarkers, or measurable signs, of aging and disease using facial analysis.
For instance, discolouration of the lips may be a sign of anemia, a lack of red blood cells or hemoglobin.
Georgievskaya adds there's another, more abstract motivation for learning how machines evaluate appearances – one that's perhaps worth considering the next time you ask an app for lipstick or hair colour advice.
"In the future, I think we will always interact with robots, and it's a good idea to know, will robots like us? What will they think about us?" she says. "Everything is becoming digital and robots are becoming so smart, we should also think about how robots perceive humans."
Wency Leung