ҳ

18 October 2021

Research into facial recognition has been under way for a long time, but has really taken off in recent years. “The technology is beginning to be used in more and more contexts”, says Jörgen Ahlberg, researcher in computer vision.

Facial recognition
Most people associate facial recognition with the police’s ability to identify suspects. For instance, computer software matches faces from CCTV with faces from police records.
But facial recognition has a number of other applications: everything from preventing unauthorised individuals from starting electric bikes, to simplified log-in on mobile phones and computers, to social surveillance of citizens.

Rapid identification

Jörgen AhlbergJörgen Ahlberg Photo credit Teodor AxlundJörgen Ahlberg is a researcher in computer vision at the Department of Electrical Engineering, and co-founder of Visage Technologies, a company in facial recognition development.
“Facial recognition existed 20 years ago, but with today’s technology, identification is astonishingly fast and more reliable than if people manually scan through images in a database”, says Jörgen Ahlberg.
One result of this is more efficient police work.
“The volume of images and video that computers can search through in a few minutes would in the past have taken the police several weeks. Now the police have a system in operation for this.”

Preventing terrorist crime

Jörgen Ahlberg brings up both advantages and disadvantages of the possibilities presented by facial recognition.
Besides fighting crime, he mentions traffic safety.
“Facial recognition in cars can mean that an unauthorised person is not able to start the car, for instance in an attempted car theft or terrorist crime.”

Privacy issues

The principal disadvantage relates to individual privacy. The technological capabilities mean that people can be recognised anywhere and anytime.
“In Sweden, most people have a lot of trust in government authorities, and we have strong legislation in this field. Therefore we are not very worried that the authorities will become like in China, where the authorities follow the citizens as they move around in their cities. Personally I find it worrying that private individuals can create their own facial recognition registers, which has happened in Russia and other countries.”

Changed behaviour

Jörgen Ahlberg believes that the technology will develop even more during the coming decade, but that technology for avoiding recognition will also make a big leap forward. And he predicts that we will have to get used to being recognised in more and more contexts.
“If someone takes a photo where I’m in the background, I can probably be recognised. How this will affect our behaviour I don’t know, but we’ve already changed our behaviour as a result of social media. People have become more cautious when it comes to posting personal images, compared to when Facebook was new.”

Traffic safety

As for traffic and transportation, Jörgen Ahlberg expects that developments in traffic safety will be even greater.
“The car will keep an eye on you so you don’t fall asleep, to ensure it’s the right driver and so on. The same goes for air traffic controllers, pilots and truck drivers. There will be systems that monitor them, that they do what they’re supposed to do, in order to prevent dangerous situations.”

Translation: Martin Mirko

Latest news from LiU

En grupp människor som sitter vid ett bord framför en folkmassa.

Participants in UN climate meetings want greater focus on implementation

UN climate negotiations are often criticised for moving too slowly. A new study published in Nature Climate Change examines what changes government delegates and other participants at the COP29 UN climate conference would like to see.

Neil Lagali vid utrustning för att undersöka ögonen.

Eye problems after COVID-19 can now be explained

Mild COVID-19 can cause severe and long-lasting eye problems, according to a study from LiU. The study also explains why it has been difficult for sufferers to get help: the abnormal eye behaviour cannot be detected by standard methods.

A woman kneeling down in a garden picking plants.

When soil becomes data – how digitalisation affects knowledge of soil health

How do we know whether soil is healthy? A new study from ҳ shows that as knowledge about soil is increasingly translated into digital data, important insights about its biological life and local context risk being overlooked.