FB pixel

Microsoft retrains facial recognition AI to better recognize gender across skin tones

 

Microsoft has improved the capability of its facial recognition technology to recognize the gender of people with darker skin tones, reducing error rates by up to 20 times, according to an announcement in a blog post.

Error rates for all women were reduced by nine times, the company says, significantly reducing the differences in accuracy across different demographics for its Face API, delivered via Azure Cognitive Services. Microsoft’s Face API team expanded and revised the datasets used for training and benchmarking, launched new data collection efforts to improve the diversity of training data, and improved the classifier to produce more precise results.

M.I.T. Media Lab Researcher Joy Buolamwini and Microsoft researcher Timnit Gebru found that leading facial recognition systems from Megvii, Microsoft, and IBM returned results with major differences in accuracy between different demographics in a study released earlier this year.

“We had conversations about different ways to detect bias and operationalize fairness. We talked about data collection efforts to diversify the training data. We talked about different strategies to internally test our systems before we deploy them,” said Microsoft Senior Researcher Hanna Wallach, an expert on fairness, accountability and transparency in AI systems.

Microsoft has also been working on a tool for engineers to automatically detect bias in AI algorithms.

The tech industry has been forced to work to reduce bias in algorithms by increased public awareness, which has also resulted in a declaration by human rights groups calling for an ethical framework based on international human rights law to be applied to machine learning systems, and hearings on the issue by the Subcommittee on Information Technology of the U.S. House Oversight and Government Reform Committee.

Article Topics

 |   |   |   |   | 

Latest Biometrics News

 

Findynet funding development of six digital wallet solutions

Finnish public-private cooperative Findynet has announced it will award 60,000 euros (US$69,200) to six digital wallet vendors to help translate…

 

Patchwork of age check, online safety legislation grows across US

As the U.S. waits for the Supreme Court’s opinion on the Texas case of Paxton v. Free Speech Coalition, which…

 

AVPA laud findings from age assurance tech trial

The Age Verification Providers Association (AVPA), and several of its members, have welcomed the publication of preliminary findings from the…

 

Sri Lanka to launch govt API policies and guidelines

Sri Lanka’s government, in the wake of its digital economy drive, is gearing up to release application programming interface (API)…

 

Netherlands’ asylum seeker ID cards from Idemia use vertical ICAO format

The Netherlands will introduce new identity documents for asylum seekers Idemia Smart Identity, compliant with the ICAO specification for vertical…

 

Zenoo integrates Trinsic, Sumsub for advanced digital ID onboarding options

Onboarding and compliance orchestration engine provider Zenoo has formed a pair of partnerships to give its customers a broader range…

Comments

Leave a Reply

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

Biometric Market Analysis

Most Viewed This Week

Featured Company

Biometrics Insight, Opinion

Digital ID In-Depth

Biometrics White Papers

Biometrics Events