All Your Face Are Belong to Us
All Your Face Are Belong to Us
Facial recognition is exploding. Find out just how good it is today.
Join the DZone community and get the full member experience.Join For Free
Hortonworks Sandbox for HDP and HDF is your chance to get started on learning, developing, testing and trying out new features. Each download comes preconfigured with interactive tutorials, sample data and developments from the Apache community.
Earlier this year I wrote about a new technology that was aiming to make CCTV smarter. It used machine learning to monitor our behavior in the store and predict if we were about to break the law.
“CCTV captures thousands of potentially useful clips everyday, such as thefts, assaults, mugging and people collapsing on the street from medical emergencies. However, due to the lack of manpower, we currently cannot analyse this footage. It’s a problem that irritates me. I worked in my Dad’s wholesale warehouse and at Buckingham Palace and felt powerless to see stock that I put out being stolen or being frisked when leaving work to make sure that I hadn’t taken anything. My co-founder actually built CCTV software to detect copper cable thieves- it was a huge problem with hundreds of people losing out on power when these were stolen,” co-founder Raz Ghafoor said recently.
The technology is one of a number of projects aiming to make security smarter. For instance, a recent project was rolled out in a number of airports to deploy facial recognition to conduct security checks on travellers as they move about the airport rather than relying on existing security procedures.
“When a lot of people gather in one place, queues develop quickly,” the researchers say. “Rather than stop every single person at an airport gate, we’ve developed algorithms that recognize people’s faces, based on electronic passports with a photo and ID number.”
Taking It Outside
Of course, what unites both of these projects is that they happen in an enclosed space. A Chinese project is aiming to be much more expansive however.
They’re aiming to equip police vehicles with 360-degree cameras that are capable of monitoring the faces of people on the street and scanning their database for known criminals.
The product has been developed by the University of Electronic Science and Technology, and is capable of scanning the faces of people within a 60 meter radius of the vehicle.
As it scans our faces, the technology will filter against the police databases for everything from age, race and gender. Equally impressively, the cameras are capable of doing their job as the car speeds along at up to 120 km/hr whilst automatically notifying the driver if they spot a known criminal.
That it can do this so quickly on a database of some 1.3 billion people is an impressive, albeit quite scary, feat. Whilst it has clear applications in chasing criminals, with China sadly known for squashing dissidents, it also has much darker applications.
It does seem as though such facial recognition technology is coming of age however, so it’s only a matter of time before we see similar applications in western countries.
Published at DZone with permission of Adi Gaskell , DZone MVB. See the original article here.
Opinions expressed by DZone contributors are their own.