UNIVERSITY PARK, Pa. — A trio of enterprising Penn Staters will travel to Paris to compete in the world finals of the 2018 L'Oréal Brandstorm on May 17. In the competition, they will pitch their "smart mirror" prototype and compete against teams from around the world for awards for the best innovative technology, most socially responsible campaign, and top overall brand.
Team SalonAI, which was selected as one of the top two teams in the U.S., is made up of 2018 Penn State graduates Vincent Trost (data sciences) and Vamshi Voruganti (industrial engineering), and senior Yuya Ong (data sciences).
Started in 1992, Brandstorm is L'Oréal's annual competition that challenges teams of college students to develop innovative ideas and business cases for some of the French beauty and personal care company's 24 international brands. This year's event included more than 34,000 registrants representing 50 countries, and asked teams of students to invent the professional salon experience of the future by using modern technologies that attract and engage millennials and increase customer loyalty to their stylists.
The making of a smart mirror
As members of Nittany Data Labs, Trost, Voruganti and Ong have spent several years exploring new applications of data sciences. Recognizing that salon interactions are most often based around a mirror, SalonAI is aiming to bring the mirror into the 21st century by using computer vision technology, machine learning algorithms, and data collection infrastructure.
To create the mirror, Ong programmed facial recognition software that identified key points on the user's face — such as the distance between the eyes and the curve of the jawline — to determine face shape. Trost used an algorithm to determine which hairstyles were seen on models with different face shapes featured in various beauty catalogs. By combining the two, the mirror can recommend and simulate hairstyles and cosmetic products that are popular among others with similar features.
"With this system, we can better analyze many features including facial shape, age, skin tone, and other critical information about a customer in real time," said Ong in the team's video pitch. "By leveraging this data we can better deliver a higher quality of services than ever before and will generate tremendous brand loyalty."
Ong built the mirror in his dorm room over two days using an old computer monitor and spare parts he found online. He then created the entire facial tracking algorithm in 24 hours during HackPSU.