Facial Age Estimation [white paper]

Yoti 2 min read

Making it faster and safer to prove your age

Our age estimation technology accurately estimates a person’s age by looking at their face. We built it to give everyone a secure and private way of proving how old they are in different everyday scenarios: from age checking on social platforms and online stores, to supermarket self-checkouts, bars and clubs. This privacy-friendly approach to age verification doesn’t require any personal details or documents, and all information is instantly deleted once someone receives their estimated age – nothing is ever viewed by a human.


Key takeaways from the report

  • Our age estimation ‘always forgets a face’.
  • The current accuracy rates (Mean Absolute Errors) are:
    • 2.79 years for 6-60 year olds
    • 1.55 years for 13-19 year olds.
    • 1.28 years for 6-12 year olds.
  • Users are not individually identifiable.
  • Our training data is collected in accordance with the UK GDPR.
  • The algorithm is trained on skin tone and gender: our best MAE is for 6-12 year olds with darkest skin tones (V & VI). The chart below shows MAE across skin tones for 6-12, 13-17 and 18-24 year olds. For skin tone classification, we use a scheme based on the widely used Fitzpatrick scale.