New AI tool to identify knives could ‘transform’ policing of knife crime
13 February 2025, 06:44
Researchers at the University of Surrey have created a tool which can quickly identify weapons and help track their origins.
A new AI system trained to identify knives could help “transform” how police forces tackle knife crime, researchers have said.
Knife Hunter, a system developed by the Institute for People-Centred AI at the University of Surrey, can help police forces identify weapons and then trace their origins more quickly, and has been developed in collaboration with the Metropolitan Police.
The research team said it can allow police to more easily log weapons found, recovered or seized, trace retail or illegal import channels and monitor geographical trends – as well as see reports the system generates on knife crime patterns to help support policing and inform policymaking.
More than 50,000 knife crime offences were recorded in England and Wales in the 12 months to June 2024 – a 4% rise on the previous year.
Professor Miroslaw Bober, the project lead at the Institute for People-Centred AI at the University of Surrey, said he hoped the system could be rolled out widely to other police forces and local authorities, having been used in a trial as part of the Met’s Operation Spectre, which aims to tackle knife crime.
“For the past three years, we’ve partnered with the Metropolitan Police to develop a system that we believe could revolutionise how forces across the country tackle knife crime in the not-too-distant future,” Professor Bober said.
“Knife Hunter transforms the way police process and analyse images and videos, doing it faster and more efficiently.
“More importantly, it’s a major step forward in helping uncover the origins of weapons in our communities.
“Looking ahead, we’re excited about the potential for Knife Hunter and similar tools to work hand-in-hand with Police and local communities to create safer streets for everyone.”
The system powering Knife Hunter has been trained on a dataset of over 25,000 images of 550 different knife types, and as a result is able to identify even the most subtle distinguishing features of a weapon, regardless of the viewing angle or lighting conditions, the researchers said.
Professor Adrian Hilton, director of the Institute for People-Centred AI said the project was a timely example of AI technology being used for societal good.
“This research innovation is timely. At a time when the UK Government is trying to rebalance their approach to AI, from leading with risk management and safety to placing seizing the opportunities for AI to improve lives front and centre, we’re showing how people-centred AI can transform lives and communities for the better,” he said.
“Working with public sector and commercial partners across a range of grand challenges – in this case with the police to make the streets safer – we’re harnessing the power of AI for good.”
Science and Technology Minister Peter Kyle said: “AI has the potential to support police in stopping these awful attacks and save lives.
“This is just the tip of the iceberg of what AI could do for our nation, on top of transforming healthcare, boosting productivity and putting time back in people’s hands – supporting our Plan for Change.”
