Researchers at the University of the West of England (UWE Bristol) are working on a commercial version of their 3D facial recognition system.
“Our system produces what is effectively a finger print of the face”
The team at the Centre for Machine Vision have been working on the technology for the last ten years which aims to make face recognition more accurate by using depth information from the face to look at scars and skin texture.
“Current available 2D systems may be fooled into incorrect identification whereas our 3D solution provides pinpoint accuracy mapping your face down to skin texture levels,” said Lyndon Smith, Professor of Computer Simulation and Machine Vision at the Centre, which is part of the Bristol Robotics Laboratory. The group’s particular expertise is in 3D reconstruction and surface inspection.
“Our system produces what is effectively a finger print of the face – showing up fine detail and blemishes such as scars or wrinkles. The solution is quicker and more effective than fingerprint or iris recognition, which are more obtrusive to use,” he said.
Putting it to the test
The team has backing of £170,000 from InnovateUK for a two year project to test out the technology in different applications with challenging environments.
The team has developed a unique database of raw face images with four versions of each face. A wide range of volunteers were imaged on many occasions over a period of months, allowing extensive testing of new methods as people change over time, and these volunteers came from industry, not a controlled lab environment. The next step is to expand the database for the new applications.
“Facial recognition technology is a powerful technique with many security application”
“This funding is for us to go ahead and commercially implement the technology. We think it’s on the verge of becoming really big,” he said. “Facial recognition technology is a powerful technique with many security applications – it might be that you are running a retail store or restaurant chain and there are certain customers you don’t want entering the premises,” said Smith. “Alternatively, it could be used at a railway station to check everyone has bought a ticket, or a live sporting venue to allow access to your registered VIPs.”
“Potential uses are increasing all the time but first we have to iron out problems with how the technology performs,” he said. “Things which are easy for the human eye to deal with, like changes in background light and people looking in different directions, are big problems for this technology. There’s a difference between making the system work in the laboratory and doing so in a busy supermarket, where there are changes in lighting conditions and people walking around in the background.”
The researchers are working with Customer Clever, based in Nottinghamshire, that already uses face recognition technology in a range of sectors, including retail. Its technology is already used at UK airports and football stadiums.
The Centre for Machine Vision is also working on projects such as automated weed imaging
- You may like: BRL opens up its research to industry
Shona Wright
Shona covers all things editorial at TechSPARK. She publishes news articles, interviews and features about our fantastic tech and digital ecosystem, working with startups and scaleups to spread the word about the cool things they're up to.
She also oversees TechSPARK's social media, sharing the latest updates on everything from investment news to green tech meetups and inspirational stories.
