Innovatrics’s facial recognition algorithm beat out more than 100 competitors to take first place in the ‘wild images’ category in an ongoing Face Recognition Vendor Test (FRVT) conducted by the National Institute of Standards and Technology (NIST).
The wild face dataset used in the test is designed to simulate real-world scenarios. It challenges facial recognition algorithms to find specific faces, even when the lighting is bad and those faces are obscured by hair or other objects. The testing shows that the Innovatrics algorithm did that particularly well, making it a reliable solution for digital onboarding and other security and surveillance applications.
“Our long-term focus is on leveraging AI technology to identify and verify real-world faces as accurately as possible,” said Marián Beszédeš, the Head of Research and Image Processing at Innovatrics. “This result is a confirmation of our team’s efforts to continuously improve and deliver the best face recognition solutions on the market.”
The facial recognition algorithm is used across the Innovatrics portfolio, and is a key component of each of its facial recognition solutions. That includes SmartFace, as well as the recently updated ABIS 7 multimodal suite and the selfie-based Digital Onboarding Toolkit.
April 15, 2019 – by Eric Weiss