Facebook picks up facial recognition startup FacioMetrics

Facebook has acquired facial recognition startup FacioMetrics for an undisclosed amount.

Using facial image analysis to determine emotions, FacioMetrics is aimed at a range of sectors including gaming, healthcare, augmented reality, and robotics.

FacioMetrics founder and CEO Fernando De la Torre said the company’s facial image analysis technology offers several applications including augmented/virtual reality, animation, and audience reaction measurement.

According to a report by ZDNet, the technology was born out of Carnegie Mellon University regarding computer vision and machine learning algorithms for facial image analysis.

“Over time, we have successfully developed and integrated this cutting-edge technology into battery-friendly and efficient mobile applications, and also created new applications of this technology,” said De la Torre, adding that the acquisition should enable FacioMetrics to advance its work “at an incredible scale, reaching people from across the globe”.

Facebook currently uses face recognition software to suggest tags for images, which calculates a unique number based on a user’s facial features, such as the distance between the eyes, nose, and ears.

These ‘face templates’ are based on profile pictures and photos that users have been tagged in on the social media website.

“How people share and communicate is changing and things like masks and other effects allow people to express themselves in fun and creative ways,” Facebook said. “We’re excited to welcome the FacioMetrics team, who will help bring more fun effects to photos and videos and build even more engaging sharing experiences on Facebook.”

Previously reported, security and computer vision researchers from the University of North Carolina said that would-be criminals could exploit social media images to dupe certain facial recognition technology.

Article Topics

acquisitions  |  biometrics  |  Carnegie Mellon University  |  computer vision  |  Facebook  |  facial recognition  |  machine learning