Summary
This white paper presents Yoti's facial age estimation technology, which determines a person's age from an image of their face without requiring physical document checks or human intervention. The technology is designed to be accurate across various skin types and genders, adhering to GDPR principles of privacy by design. It emphasizes data minimization by only requiring a facial image for age estimation, with all images deleted immediately after processing. The paper details the True Positive Rates (TPRs) for different age groups, showing high accuracy levels, particularly for 13 to 17-year-olds with a TPR of 99.91%. It also discusses the algorithm's training process, ethical considerations, and continuous improvements in accuracy while minimizing bias across demographics. The document outlines the importance of ensuring that users can only access age-appropriate content and highlights Yoti's commitment to ethical data usage and compliance with regulatory standards.
