Face masks foil face recognition systems

The widespread use of masks must mark a “step change” in how identity is managed and the way facial recognition biometrics are developed and applied, says the Biometrics Institute.

The Biometrics Institute is an independent international organisation for biometric users, and includes banks, airlines, government agencies, biometric experts, privacy experts, suppliers and academics among it membership.

A latest report from the US National Institute of Standards and Technology (NIST) on the accuracy of face recognition algorithms “is a reminder that biometric solutions need careful evaluation and risk management”, says the Institute.

That report found that algorithms submitted after the pandemic “continue to give increased false non-match rates when facial images are masked”.

Using the highest coverage mask, the most accurate algorithms fail to authenticate 5 per cent of people compared to 0.3 per cent without masks, said the report.

And some algorithms that are “quite competitive with unmasked faces” still fail to authenticate between 10 per cent and 40 per cent of masked images, found the NIST report.

The first report published in July by NIST found that even the best of the 89 commercial facial recognition algorithms tested, had error rates of between 5 per cent and 50 per cent in matching digitally-applied face masks with photos of the same person without a mask.

The new second report tested another 65 face recognition algorithms provided to NIST after mid-March this year.

The Biometrics Institute said face biometrics where masks are used must be “carefully risk managed to maintain safety, public confidence and security”.

Isabelle Moeller, chief executive of the Biometrics Institute, said: “Further research and testing may reveal that using additional sensor data - like high resolution, 3D or infrared - can improve accuracy.

“However, a theme common to all NIST’ tests on face recognition is that each algorithm performs differently. Now more than ever, it’s vital that anyone using biometrics makes a point of understanding the limitations of their individual algorithm.”

The Biometrics Institute has recently released its new tool, the Good Practice Framework, which helps anyone planning to introduce a biometric system or develop an existing application to formulate “sound policies and processes” before they apply the technology.

    Share Story:

Recent Stories