On Facial Age Estimation, improvements and updates

profile picture Matt Prendergast 3 min read
People with their estimated ages

We continue to invest in improving the accuracy of our world-leading facial age estimation and we will soon be releasing a new ‘Jan 2023’ model with improved accuracy across all skin tones and gender for those aged 6-70.

At Yoti we constantly strive to improve all our services given our commitment to tech for good, and given the growing market importance of these services and increasing regulatory engagement. For example, coming soon we’ll be introducing multiple, concurrent age estimation models, which will help improve accuracy even further, whilst still completing a check within seconds. 

We will also continue to update our Yoti Age Estimation white paper, now 4 years old this month, in which we transparently publish our accuracy across age, gender and skin tones by year between ages 6 and 70. We expect to publish the updated white paper in the next couple of weeks but importantly, we can share today our Jan 2023 model further improves our accuracy and further reduces bias.

Across all age ranges, gender and skin tones we are seeing a 5.1% increase in accuracy, reducing the weighted average MAE for 6 to 70 year olds from 3.0 to 2.8 years. As you can see below for this model we have been focussing on reducing the discrepancy between light skintones (tone 1) and darker skin tones (tone 3) We recognise our work is not finished in this regard.

Table displaying yoti's facial age estimation improvements over time, with an average of 5.1% improvement across all skin tones and genders from May 22 to Jan 23
Table shows mean average error (MAE) for age range 6-70 by gender and skin tone, and the percentage improvement from our May 2022 model to our January 2023 model.

So, well done for marking your own homework, you might say! But we are happy to report our May 2022 white paper has been independently verified as to the measurement methodology and accuracy of our results. On the request of one of our clients, the ACCS undertook an independent evaluation of our May 2022 white paper and had this to say:

“The training, testing and results reporting presented in the whitepaper have been independently validated by ACCS, who have certified that Yoti have deployed appropriate methodologies to analyse the performance of their Age Estimation algorithm, including ensuring appropriate separation of machine learning training data, testing data and validation data.”

In addition to this, we are also happy to announce that we have been invited to participate in a workshop on ICO commissioned research on the measurement of age assurance on Thursday 19th January, in London organised by ACCS and AVPA. 

Follow us on LinkedIn to stay abreast of Yoti news or get in touch to find out more. 

Related stories

How accurate can facial age estimation get?

Facial age estimation using machine learning has advanced significantly in recent years. But, a common and fair question still arises: How accurate can it really be? Can a system look at your face and accurately guess your age, especially when humans often get it wrong? The short answer is that it’s very accurate – but not perfect. We explain why.   The myth of 100% accuracy It’s important to set realistic expectations. No facial age estimation model can achieve 100% accuracy across all ages.  Human aging is highly individual and shaped by many external factors, especially as we get

6 min read
An image of the Yoti logo. Underneath reads "Yoti responds to the Supreme Court decision on Free Speech Coalition vs Paxton".

The Supreme Court rules in favour of age verification

The question of whether states can require age checks on adult websites has reached a turning point in the US courts. In Free Speech Coalition v. Paxton, the case challenged Texas’s H.B. 1181 law, which required commercial websites that publish sexually explicit content to verify the ages of their visitors to prevent minors from accessing pornography. One of the big discussion points has been whether, in 2025, it is still too burdensome for US adults to prove age privately compared to 20 years ago – especially when privacy-preserving age verification tools have advanced significantly.  The Supreme Court has upheld

3 min read
An image of a child and their parent sitting on a sofa and using a mobile phone. The accompanying text reads 'Ireland's Online Safety Code - Ireland'.

Ireland’s Online Safety Code: what it means for online platforms and how to comply

What you need to know: Ireland’s Online Safety Code will hold video-sharing platforms accountable for keeping their users, especially children, safe online. Platforms with adult content, including pornographic or extremely violent content, must use age assurance to prevent children from accessing the content. These age assurance requirements come into force in July 2025. Platforms that don’t comply can face strong penalties – up to €20 million or 10% of annual turnover.     From July 2025, video-sharing platforms in Ireland with pornography or extremely violent content will need to introduce age assurance to protect children from accessing their content.

7 min read