FB pixel

Yoti updated transparency report on biometric age verification shows further accuracy gains

 

biometric facial recognition

Yoti has improved the accuracy of its biometrics-based age estimation algorithm for the important 13 to 15 year age group, according to internal benchmarking.

The company updated its transparency efforts for its age scanning accuracy, publishing a summary version of its Age Estimation white paper to its website.

The white paper provides details on Yoti’s efforts to build up biometric training data for its model, information on how people can opt out of research and development projects, and reviews the transparency efforts the company makes with the onboarding and opt-out screens of the Yoti app.

Compared to Yoti’s previous age estimation transparency report, the company’s algorithm has reduced the mean average error (MAE) rate for 13-to-15 year-olds from 1.60 to 1.35, and its overall MAE rate across all age groups from 2.28 to 2.19.

Yoti recommends setting the age threshold higher than the age of interest, in order to create a ‘buffer’ for “an acceptably low false positive rate.”

The company’s biometric age estimation technology was recently deployed for a pilot by several UK supermarkets to prevent underage alcohol purchases.

Article Topics

 |   |   |   |   |   |   |   |   | 

Latest Biometrics News

 

Biometrics adoption strategies benefit when government direction is clear

Biometrics providers have major growth opportunities ahead where there is clarity about their role. What part governments play in digital…

 

Biometric Update Podcast digs into deepfakes with Pindrop CEO

Deepfakes are one of the biggest issues of our age. But while video deepfakes get the most attention, audio deepfakes…

 

Know your geography for successful digital ID adoption: Trinsic

A big year for digital identity issuance, adoption and regulation has widened the opportunities for businesses around the world to…

 

UK’s digital ID trust problem now between business and government

It used to be that the UK public’s trust in the government was a barrier to the establishment of a…

 

Super-recognizers can’t help with deepfakes, but deepfakes can help with algorithms

Deepfake faces are beyond even the ability of super-recognizers to identify consistently, with some sobering implications, but also a few…

 

Age assurance regulations push sites to weigh risks and explore options for compliance

Online age assurance laws have taken effect in certain jurisdictions, prompting platforms to look carefully at what they’re liable for…

Comments

Leave a Reply

This site uses Akismet to reduce spam. Learn how your comment data is processed.

Market Analysis

Most Viewed This Week

Featured Company

Biometrics Insight, Opinion

Digital ID In-Depth

Biometrics White Papers

Biometrics Events