Monday, September 28, 2020
Home Lead Story Microsoft's Improved Face API More Accurately Recognizes a Range of Skin Tones

Microsoft’s Improved Face API More Accurately Recognizes a Range of Skin Tones

Currently, facial recognition tools tend to perform best on men with lighter skin and worst on women with darker skin

Addressing two weak points in the currently available face recognition technologies, Microsoft has updated its facial recognition tools that can better identify people with darker skin tones than before.

With the new improvements, the tools were able to reduce the error rates for men and women with darker skin by up to 20 times.

“For all women, the error rates were reduced by nine times. Overall, with these improvements, they were able to significantly reduce accuracy differences across the demographics,” Microsoft said in a blog post written by John Roach late on Tuesday.

Currently, facial recognition tools tend to perform best on men with lighter skin and worst on women with darker skin.

“That improvement addresses recent concerns that commercially available facial recognition technologies more accurately recognised gender of people with lighter skin tones than darker skin tones, and that they performed best on males with lighter skin and worst on females with darker skin,” Roach wrote.

Representational image.
Representational image. Wikimedia Commons

The higher error rates on females with darker skin highlights an industrywide challenge — Artificial Intelligence (AI) technologies are only as good as the data used to train them.

If a facial recognition system is to perform well across all people, the training dataset needs to represent a diversity of skin tones as well as factors such as hairstyle, jewellery and eyewear.

The team responsible for the development of facial recognition technology at Microsoft, which is available to customers as the Face API via Azure Cognitive Services, worked with experts on bias and fairness across Microsoft to improve a system called the gender classifier, focusing specifically on getting better results for all skin tones.

Also Read: Microsoft Brings AI-powered Visual Search to Bing

“We had conversations about different ways to detect bias and operationalise 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 Hanna Wallach, Senior Researcher in Microsoft’s New York research lab.

Wallach and her colleagues provided “a more nuanced understanding of bias,” said Cornelia Carapcea, a Principal Programme Manager on the Cognitive Services team, and helped her team create a more robust dataset “that held us accountable across skin tones.” (IANS)

STAY CONNECTED

19,133FansLike
362FollowersFollow
1,776FollowersFollow

Most Popular

The Party Culture of Hindi Film Industry

BY VINOD MIRANI The film industry was known for its party culture. The alcohol flowed freely catering to choice of all, from beer to vodka...

High Levels of Air Pollution Leads to Increase in Electricity Consumption: Study

Researchers have found that high levels of air pollution are forcing people to consume more electricity, subsequently causing even greater environmental problems by increasing...

Using Weighted Chain Blankets May Improve Sleep of Insomnia Patients

Using weighted chain blankets may lead to better sleep maintenance, a higher daytime activity level, and reduced symptoms of fatigue, depression and anxiety among...

Pandemic Will “Turn Tourists into Travellers”: Rider Mohit Kharbanda

By Puja Gupta Rider and influencer Mohit Kharbanda has covered nearly 2 lakh kilometres across India and several other countries in his motorcycle since he...

SAATHI: Ministry of Tourism Partners QCI to Assist Hospitality Industry

To assist the hospitality industry in their preparedness to continue operations safely and mitigate risks arising out of the Covid-19 pandemic, the Ministry of...

AR/VR, 3D Technologies in Online Shopping Can Enhance Consumer Purchasing: Report

As millions of people stay home in the pandemic, immersive technologies such as augmented and virtual reality and 3D content can enhance consumer purchasing...

Hockey India Conducts Online Course in a Bid to Improve Standard of Coaching

In a bid to continuously improve the standard of coaching across the country, Hockey India has been conducting the 'Basic' Level coaching course (online)...

Chatbot-Based AI Health Apps Can’t Replace a Doctor: Study

As millions of people turn to their mobile devices to talk to chatbot-based health apps, researchers have revealed that existing apps lack the functions...

Recent Comments