{"id":253,"date":"2020-10-11T17:00:21","date_gmt":"2020-10-11T17:00:21","guid":{"rendered":"https:\/\/thenextweb.com\/?p=1322335"},"modified":"2020-10-11T17:00:21","modified_gmt":"2020-10-11T17:00:21","slug":"how-facial-recognition-systems-are-adapting-to-masks","status":"publish","type":"post","link":"https:\/\/www.londonchiropracter.com\/?p=253","title":{"rendered":"How facial recognition systems are adapting to masks"},"content":{"rendered":"\n

It\u2019s surprising how quickly public opinion can change. Winding the clocks back 12 months, many of us would have looked at a masked individual in public with suspicion.<\/p>\n

Now, some countries have enshrined face mask use in law<\/a>. They\u2019ve also been made compulsory in Victoria<\/a> and are recommended in several other states.<\/p>\n

One consequence of this is that facial recognition systems in place for security and crime prevention may no longer be able to fulfil their purpose. In Australia, most agencies are silent about the use of facial recognition.<\/p>\n

But documents leaked earlier this year revealed Australian Federal Police<\/a> and state police in Queensland, Victoria and South Australia<\/a> all use Clearview AI, a commercial facial recognition platform. New South Wales police also admitted<\/a> using a biometrics tool called PhotoTrac.<\/p>\n

What is facial recognition?<\/h2>\n

Facial recognition<\/a> involves using computing to identify human faces in images or videos, and then measuring specific facial characteristics. This can include the distance between eyes, and the relative positions of the nose, chin and mouth.<\/p>\n

This information is combined to create a facial signature, or profile<\/a>. When used for individual recognition \u2013 such as to unlock your phone \u2013 an image from the camera is compared to a recorded profile. This process of facial \u201cverification\u201d is relatively simple.<\/p>\n

However, when facial recognition is used to identify faces in a crowd, it requires a significant database of profiles against which to compare the main image.<\/p>\n

These profiles can be legally collected by enrolling large numbers of users into systems<\/a>. But they\u2019re sometimes collected through covert means<\/a>.<\/p>\n

\n

<\/i><\/a>Facial \u2018verification\u2019 (the method used to unlock smartphones) compares the main image with a single pre-saved facial signature. Facial \u2018identification\u2019 requires examining the image against an entire database of facial signatures. teguhjatipras\/pixabay<\/figcaption><\/figure>\n<\/p>\n<\/figure>\n

The problem with face masks<\/h2>\n

As facial signatures are based on mathematical models of the relative positions of facial features, anything that reduced the visibility of key characteristics (such as the nose, mouth and chin) interferes with facial recognition.<\/p>\n

There are already many ways to evade or interfere<\/a> with facial recognition technologies. Some of these evolved from techniques designed to evade number plate recognition systems.<\/p>\n

Although the coronavirus pandemic has escalated concerns around the evasion of facial recognition systems, leaked US documents<\/a> show these discussions<\/a> taking place back in 2018 and 2019, too.<\/p>\n