Yoti Makes Major strides in Facial Age Estimation Accuracy Before UK OSA De

Published Date : 7/22/2025 

Yoti's facial age estimation technology has achieved new levels of accuracy, particularly for ages 13-17, ahead of the UK's Online Safety Act (OSA) deadline on July 25. The company's white paper reveals key metrics and guidelines for implementing effective age assurance. 

Yoti, a leading provider of digital identity solutions, has announced significant improvements in the accuracy of its facial age estimation technology. These advancements are detailed in a new white paper published just days before the UK's Online Safety Act (OSA) takes effect on July 25, 2025. The OSA mandates that digital platforms implement highly effective age verification methods, such as facial age estimation, to ensure the safety of young users.

The mean error rate (MEA) for Yoti’s technology in estimating the ages of individuals between 13 and 17 years old is now 1.1 years. This is a crucial improvement, especially for social media platforms that have age limits of 15 and 16 years. For the 18-to-24 age group, Yoti’s MAE has been reduced to 2.1 years.

The testing also demonstrates that Yoti’s technology can accurately estimate 99.3 percent of youths aged 13 to 17 as being under 21, and 99 percent of children aged 6 to 12 as being under 13. The variance in true positive rates (TPRs) for 13-17 year-olds across different skin tones (1, 2, and 3) is only 0.7 percent, which Yoti describes as “no discernable bias.” The MEA for individuals aged 6 to 70 is 2.4 years.

Robin Tombs, CEO of Yoti, commented, “With a growing demand for effective age assurance and increasing regulatory engagement, we have continued to invest and improve the accuracy of facial age estimation. It is fast becoming an essential tool to help protect young people online, create safer, age-appropriate experiences, and respect people’s privacy. The improved accuracy means even more people will now be able to use our privacy-preserving facial age estimation to easily prove their age online.”

The white paper also provides guidance on safety thresholds, buffer zones, and the “waterfall approach” for implementing facial age estimation. It includes evaluations of the technology by the National Institute of Standards and Technology (NIST) and the Ageing and Age Verification Committee (ACCS), along with practical lessons learned from Yoti’s experience.

The implementation of online age assurance checks in the UK is set to increase significantly, as platforms hosting adult content, including pornography websites, peer-to-peer sites, search engines, instant messaging services, and dating apps, are required to verify whether their users are children. This mandate aims to protect young users from inappropriate content and ensure a safer online environment.

Tombs further stated, “The majority of adults choose our facial age estimation to quickly and easily prove their age. For those estimated below the threshold, they can use our privacy-preserving Digital ID app or share their age from an official ID document. As age checks become more common, nearly 1 in 4 people are using a reusable age token or Digital ID to anonymously prove their age. We’re proud to be protecting children online and introducing people to privacy-first age solutions – because online safety shouldn’t come at the cost of privacy.”

Yoti’s advancements in facial age estimation technology not only meet the regulatory requirements but also enhance the privacy and safety of users, making it a valuable tool in the digital age. 

Frequently Asked Questions (FAQS): 

Q: What is the Online Safety Act (OSA) and when does it take effect?

A: The Online Safety Act (OSA) is a UK law requiring digital platforms to implement highly effective age verification methods to protect young users from inappropriate content. It takes effect on July 25, 2025.

Q: What is Yoti's mean error rate (MEA) for estimating ages of 13-17 year-olds?

A: Yoti’s mean error rate (MEA) for estimating the ages of individuals between 13 and 17 years old is now 1.1 years.

Q: How does Yoti's technology perform in terms of true positive rates (TPRs) for different age groups?

A: Yoti’s technology correctly estimates 99.3 percent of youths between 13 and 17 as being under 21 and 99 percent of children between 6 and 12 as being under 13.

Q: What is the 'waterfall approach' mentioned in Yoti's white paper?

A: The 'waterfall approach' is a method for implementing facial age estimation, which involves a series of steps or thresholds to ensure accurate and safe age verification.

Q: How can users who are estimated below the age threshold prove their age?

A: Users who are estimated below the age threshold can use Yoti’s privacy-preserving Digital ID app or share their age from an official ID document to prove their age. 

More Related Topics :