Fans attending this season’s Uefa Champions League final will be scanned by face recognition cameras in Cardiff’s Principality Stadium as part of a police operation.
Faces will be scanned at the arena – formerly the Millennium Stadium – and Cardiff’s central railway station. South Wales Police said the image can then be matched against hundreds of thousands of ‘custody images’ stored by regional forces.
The stadium can hold around 74,500 spectators, while a further 100,000 fans are expected to travel to Cardiff for the June 3 game. The Champions League semi-finalists who could reach Cardiff are Real Madrid, Atletico Madrid, Juventus and Monaco.
The BBC news website said police intend to use the system to scan faces at various locations, but it will not be a condition of entry to the stadium.
Police said the operation is an attempt to further test Automated Facial Recognition (AFR) technology.
“The Uefa Champions League finals in Cardiff give us a unique opportunity to test and prove the concept of this technology in a live operational environment, which will hopefully prove the benefits and the application of such technology across policing,” South Wales Police said in a statement.
“This will be one of the largest security operations ever undertaken in the Welsh capital and the use of technology will support the policing operation which aims to keep people safe during what will be a very busy time in Cardiff.”
The operation will build on previous police use of AFR technology by the Metropolitan Police during last year’s Notting Hill Carnival.
Speaking to the Motherboard tech news website, Tony Porter, the UK Government’s surveillance camera commissioner, said that police must use the technology in compliance with the UK’s surveillance camera code of practice.
“My office has been in touch with South Wales Police to help them ensure that when deploying AFR they are complying with the code [of practice],” he said.
“I have seen the use of AFR increase [over] the past few years and a recent report by the National Institute of Standards and Technology indicated that facial recognition is a difficult challenge. Getting the best, most accurate results for each intended application requires good algorithms, a dedicated design effort, a multidisciplinary team of experts, limited-size image databases, and field tests to properly calibrate and optimise the technology.”