British Transport Police use of Live Facial Recognition Technology
Live Facial Recognition Technology
British Transport Police (BTP) is trialling the use of Live Facial Recognition (LFR) technology at railway stations.
The pilot is running for six months from 11 February 2026 at selected key transport hubs in London.
It will evaluate the effectiveness of LFR on our railways, its impact on public safety, and the public’s response to the technology.
Why are we using LFR?
The initiative follows a significant amount of research and planning, and forms part of BTP’s commitment to using innovative technology to identify and apprehend individuals wanted for serious criminal offences.
Our deployments will be intelligence-led, meaning we’ll target the technology to crime hotspots on the network where data shows us there is a likelihood of high harm offenders passing through the location.
How will it work?
Members of the public may be familiar with roadside LFR deployments already in use by other police forces.
Policing the railway represents a unique challenge, with a transient population and over three million journeys taken a day across Great Britain. Our deployments will be intelligence led, where we know we need the resources most, and see cameras temporarily in place on station concourses.
Each Live Facial Recognition deployment undergoes a full Health and Safety assessment to ensure equipment, public‑facing areas and officer roles are managed safely throughout
BTP currently utilises NEC’s NeoFace M40 algorithm facial recognition technology.
Before using LFR, a watchlist of offenders is created that are wanted by the police and courts or have ancillary court order with conditions.
LFR cameras target an area, and the images are streamed to the live facial recognition technology. The images are compared against the images in the watchlist. When the technology finds a possible match using NEC’s NeoFace M40 algorithm, an alert is generated.
An officer then compares the camera image to the person they see and decides whether to speak to the person.
We will always explain why we have chosen to speak with someone and give them an informational leaflet with contact details if they have further questions. People who are not included on a watchlist cannot be identified.
We will delete the images with alerts immediately after using them or within 24 hours. The images and biometric data of those who don’t cause an alert are automatically and immediately deleted. We record the CCTV footage that is used by the LFR cameras, and we keep it for 31 days.
Public Notification
Before each deployment, we will publish details on our website to ensure transparency.
There will be highly visible signage in place to inform the public about the operation, as well as QR codes available for feedback and further information.
Privacy
We’re committed to using LFR responsibly and transparently.
Deployments will comply with all relevant legal and regulatory standards, including the Data Protection Act 2018, Human Rights Act 1998, and Equality Act 2010, and oversight will include internal governance and external engagement with ethics and independent advisory groups.
People who prefer not to enter the recognition zone will have alternative routes available and images of anyone not on the authorised database will be deleted immediately and permanently.
Further details can be found in our policy documents below.
Evaluation
When the pilot is complete, we’ll conduct a full assessment to review outcomes, identify lessons learned, and inform future planning. We encourage anyone who encounters our use of LFR when the trial begins to engage with us so we can make sure that we’re using it in the best way and helping to make our railways as safe as possible.
Testing information
The Metropolitan Police Service (MPS) and South Wales Police (SWP) commissioned independent testing of the NEC Neoface M40 algorithm with the National Physical Laboratory (NPL). The NPL is a world-leading centre of excellence that provides cutting-edge measurement in science, engineering and technology.
The NPL test plan was specifically designed to help identify any impact this technology may have on any protected characteristics, in particular race, age and sex.
The NPL report gives an impartial, scientifically underpinned and evidence-based analysis of the performance of the facial recognition algorithm that will be used by BTP.
This report recommends a setting for use with the algorithm that minimises the likelihood of any false positive indication and adverse impact on equitability.
BTP will operate the system to build trust and confidence with the communities we serve through the use of this innovative technology.
Retrospective Facial Recognition
(Documents to follow)
Operator Initiated Facial Recognition
BTP keeps its need to use Facial Recognition technologies under review but does not presently use Operator Initiated Facial Recognition.
Upcoming deployments
Thursday 11 June - London Euston railway station
Deployment history and performance
FAQs
Frequently Asked Questions.pdf
Policy documents
- LFR - Legal Mandate
- LFR - Equality Impact Assessment
- LFR - Appropriate Policy Document 01
- LFR - Appropriate Policy Document 02
- LFR - Data Protection Impact Assessment - Stage 01
- LFR - Data Protection Impact Assessment - Stage 02
- LFR - Policy
- LFR - Policy Appendix
Contact