General Discussion
Related: Editorials & Other Articles, Issue Forums, Alliance Forums, Region ForumsFace masks are breaking facial recognition algorithms, says new government study
From https://www.theverge.com/2020/7/28/21344751/facial-recognition-face-masks-accuracy-nist-study
Stopping the spread of disease and mass surveillance
By James Vincent Jul 28, 2020, 6:10am EDT
Face masks are one of the best defenses against the spread of COVID-19, but their growing adoption is having a second, unintended effect: breaking facial recognition algorithms.
Wearing face masks that adequately cover the mouth and nose causes the error rate of some of the most widely used facial recognition algorithms to spike to between 5 percent and 50 percent, a study by the US National Institute of Standards and Technology (NIST) has found. Black masks were more likely to cause errors than blue masks, and the more of the nose covered by the mask, the harder the algorithms found it to identify the face.
With the arrival of the pandemic, we need to understand how face recognition technology deals with masked faces, said Mei Ngan, an author of the report and NIST computer scientist. We have begun by focusing on how an algorithm developed before the pandemic might be affected by subjects wearing face masks. Later this summer, we plan to test the accuracy of algorithms that were intentionally developed with masked faces in mind.
[...]
=======================================================================================
On edit::
From NIST, https://www.nist.gov/news-events/news/2020/07/nist-launches-investigation-face-masks-effect-face-recognition-software
Algorithms created before the pandemic generally perform less accurately with digitally masked faces.
July 27, 2020
Credit: B. Hayes/NIST
NIST digitally applied mask shapes to photos and tested the performance of face recognition algorithms developed before COVID appeared. Because real-world masks differ, the team came up with variants that included differences in shape, color and nose coverage.
Now that so many of us are covering our faces to help reduce the spread of COVID-19, how well do face recognition algorithms identify people wearing masks? The answer, according to a preliminary study by the National Institute of Standards and Technology (NIST), is with great difficulty. Even the best of the 89 commercial facial recognition algorithms tested had error rates between 5% and 50% in matching digitally applied face masks with photos of the same person without a mask.
The results were published today as a NIST Interagency Report (NISTIR 8311), the first in a planned series from NISTs Face Recognition Vendor Test (FRVT) program on the performance of face recognition algorithms on faces partially covered by protective masks.
With the arrival of the pandemic, we need to understand how face recognition technology deals with masked faces, said Mei Ngan, a NIST computer scientist and an author of the report. We have begun by focusing on how an algorithm developed before the pandemic might be affected by subjects wearing face masks. Later this summer, we plan to test the accuracy of algorithms that were intentionally developed with masked faces in mind.
The NIST team explored how well each of the algorithms was able to perform one-to-one matching, where a photo is compared with a different photo of the same person. The function is commonly used for verification such as unlocking a smartphone or checking a passport. The team tested the algorithms on a set of about 6 million photos used in previous FRVT studies. (The team did not test the algorithms ability to perform one-to-many matching, used to determine whether a person in a photo matches any in a database of known images).
[...]
Happy to hear that is the case.
jimfields33
(15,974 posts)Its bad enough they have our personal information. But having details of our face is unacceptable I believe.
ProfessorGAC
(65,203 posts)All that high tech, and an 80nm semi-living glob of molecules ruins it!
That's amusing.
5X
(3,972 posts)greymattermom
(5,754 posts)Instead they get recorded saying racist and other unacceptable things, and Facebook finds their bosses. If they only wore a mask, they could say whatever they want and keep their jobs, right?
Jamastiene
(38,187 posts)1. I'm not so sure that tech is all that necessary in the first place. I guess it depends on the purpose of it.
2. Humans will not quit with the stupid until there is another pandemic that affects our retinas too, if Covid doesn't find a way to do it first. It has been pretty crafty that way. Covid adapts so freaking fast and affects victims so many ways. It's alive and adapts and affects people in so many eerily creepy ways. That fucker is scary.
Sherman A1
(38,958 posts)But sunglasses are your friend in that case.
Igel
(35,359 posts)Often facial recognition sorts through things like DMV records to compare with either police cameras or surveillance cameras. The resolution isn't nearly HD enough.
too bad so sad
MissB
(15,812 posts)My phone will not unlock with a mask on.
ucrdem
(15,512 posts)I wondered what could be captivating those people stopped dead in their tracks and staring at their phones in the middle of the tomato paste aisle . . .
nuxvomica
(12,447 posts)That's just another one of those interesting reversals of the beliefs of Repub simpletons, like how a nationwide lockdown early on would've actually preserved the economy.
roamer65
(36,747 posts)I think I will keep wearing one even after the virus is tamed.
Solly Mack
(90,787 posts)Pixelated, all over Q-Bert type pattern. Bit patterned camouflage. Whichever makes sense to people.
Main thing, must be a random pattern and a computer generated pattern does it best.
WhiskeyGrinder
(22,448 posts)EllieBC
(3,042 posts)No one should have been supportive of facial recognition tech.