“Wild image evaluations are concerned with the application of facial recognition to images in which subjects are not posing for image capture, and may be angled or obscured in ways that can hinder successful identification.”
Another breakthrough in standardized testing is further burnishing the credibility of Camvi‘s AI-driven facial recognition technology.
The company has announced that it has attained a record-breaking accuracy of 99.87 percent in the University of Massachusetts’ Labeled Faces in the Wild evaluation. The ‘LFW’ test represents a globally respected benchmark evaluation along the lines of the National Institute of Standards and Technology’s Face Recognition Vendor Test, in which Camvi attained the top ranking for ‘Wild Image’ accuracy last year.
Wild image evaluations are concerned with the application of facial recognition to images in which subjects are not posing for image capture, and may be angled or obscured in ways that can hinder successful identification. As such, they represent the kinds of real-world challenges that facial recognition systems can face in surveillance applications through CCTV cameras and the like.
Commenting on the LFW record in a statement, Camvi Technologies CEO John Chen said that it “solidifies our leadership position not only in the U.S., but also in the world.” Chen also emphasized the speed and scalability of Camvi’s facial recognition solutions, asserting, “We relentlessly push the envelope in our quest for the most accurate, fastest and most scalable face recognition technology.”
January 10, 2019 – by Alex Perala