FB pixel

Cutting out clustered data points to reduce facial recognition bias explained in AFRL talk

Howard pitches bias reduction method to the community
Cutting out clustered data points to reduce facial recognition bias explained in AFRL talk
 

Despite the presence of many “heavy hitters” in the public discourse about bias in facial recognition, misunderstanding about the nature of the problem and where it comes from is widespread, according to a recent talk as part of the Applied Face Recognition Lab’s virtual talk series.

John Howard, principal data scientist of the Identity and Data Sciences Laboratory at the Maryland Test Facility, delved into the issue in a presentation titled ‘Understanding and Mitigating Bias in Human & Machine Face Recognition.’

While many observers, including many working in computer science and machine vision, emphasize the role of data as a cause of bias in biometric algorithm performance, Howard notes that there are many possible sources.

“I also think just blaming the data is, frankly, a way to dodge what are probably more challenging and more interesting issues,” Howard explains. This is a tendency that is attractive, because it leads to a resolution that data scientists are used to and comfortable with; the ingestion of more data.

Loss function, evaluation bias, and the way that people relate to machines are important to a more complete understanding of the issue of bias in facial recognition, Howard argues. The latter issue includes projection bias, confirmation bias, and automation bias. In other words, people tend to expect machines to behave like them, confirm their beliefs, and produce results that do not need to be verified.

Face is a newer biometric modality than fingerprint and iris, Howard, says, and lessons can possibly be taken from the two older modalities of the “big three.” “Unique problems” may be presented by elements unique to the face modality, however.

The false matches produced by iris recognition algorithms, for instance, often cross between genders and ethnicities, while those in face do not. This makes it harder for people to spot errors in face matching, despite the same terminology (“false match error”) being used in each case.

Howard reviewed several research papers demonstrating how different biases. Automation bias is modest, and in ideal circumstances shows up mostly when people are unsure, for instance. When circumstances are less ideal, like when people are wearing masks, people are more likely to privilege a computer’s assessment.

He also reviewed the effect of “broad homogeneity” and findings of NIST’s FRVT Part 3, which assesses bias in algorithms on an individual basis.

Ultimately, while faces do contain similar or ‘clustered’ data based on demographics, Howard emphasizes that research indicates it is possible to select particular data points that do not exhibit clustering, to reduce the false matches errors that amount to bias in face biometrics, particularly when a human is in the loop. This is because the algorithms return candidate lists that suddenly look more like those in fingerprint and iris recognition. The right candidate, in many cases, is obvious to the human eye.

Article Topics

 |   |   |   | 

Latest Biometrics News

 

Biometrics connecting ID and payments through digital wallets, apps and passkeys

Biometrics are connecting with payment credentials, whether through numberless credit cards and banking apps or passkeys, as the concrete steps…

 

Reach of Musk, DOGE’s federal data access sets off privacy, security alarms

Led by tech billionaire Elon Musk and a shadowy team believed to be under his control, the United States DOGE…

 

Mobile driver’s licenses on the cusp of ‘major paradigm shift’

More entities have integrated the California mobile driver’s license (mDL) credential for identity verification. Although just 15 states have introduced…

 

Gesture-based age estimation tool BorderAge joins Australia age assurance trial

Australia’s age assurance technology trial is testing the new biometric tool that performs age estimation based on hand gestures. The…

 

European AI compliance project CERTAIN launches

The pan-European project to create AI compliance tools CERTAIN has kicked off its work, with the goal of making European…

 

Signaturit Group acquiring Validated ID for undisclosed sum

Spain-based digital identity and electronic signature provider Validated ID is being acquired by Signaturit Group, a European company offering identity…

Comments

Leave a Reply

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

Most Viewed This Week

Featured Company

Biometrics Insight, Opinion

Digital ID In-Depth

Biometrics White Papers

Biometrics Events