Summary: accuracy and equitability evaluation of Idemia facial recognition algorithm for Home Office strategic facial matching
Published 4 December 2025
© Crown copyright 2025
This publication is licensed under the terms of the Open Government Licence v3.0 except where otherwise stated. To view this licence, visit nationalarchives.gov.uk/doc/open-government-licence/version/3 or write to the Information Policy Team, The National Archives, Kew, London TW9 4DU, or email: psi@nationalarchives.gov.uk.
Where we have identified any third party copyright information you will need to obtain permission from the copyright holders concerned.
This publication is available at https://www.gov.uk/government/publications/facial-recognition-technology-tests-national-physical-laboratory/summary-accuracy-and-equitability-evaluation-of-idemia-facial-recognition-algorithm-for-home-office-strategic-facial-matching
Independent Testing of Facial Recognition Technology: National Facial Recognition Algorithm for a New National Facial Matching Service
Why test facial recognition (FR) systems?
The Home Office, in collaboration with the Office of the Police Chief Scientific Adviser (OPCSA) and the National Police Chiefs’ Council (NPCC), commissioned independent testing of the Facial Recognition (FR) algorithm which is intended to be used within a new national facial matching service.
The independent testing was conducted by the National Physical Laboratory (NPL), a world-leading centre of excellence that provides cutting-edge measurement in science, engineering and technology. The aim of the independent testing was to develop an in-depth understanding of the equitability and performance of the algorithm when it was being used in operational environments for Retrospective Facial Recognition (RFR) and Operator Initiated Facial Recognition (OIFR).
The IDEMIA MBSS FR algorithm, which will be used within a new national facial matching service, was selected by the Home Office in an open and competitive procurement, which included selection criteria based upon the performance of bidders’ algorithms in the Home Office test environment.
The NPL testing utilised a similar, but not identical, methodology and dataset to testing conducted on the NEC NeoFace algorithm in 2023 for the Metropolitan Police Service and South Wales Police[footnote 1] and for testing of the algorithm used within the Police National Database (PND) and was specifically designed to help identify any impact this technology may have on any protected characteristics, in particular race, age and gender.
What is Retrospective Facial Recognition?
Retrospective Facial Recognition (RFR) is used after an event or incident as part of a criminal investigation when the police need to identify someone. Images are typically supplied from CCTV, mobile phone footage, dashcam or doorbell footage or social media. These images are then compared against images of people taken on arrest to identify a suspect.
Specially trained operators visually assess the images returned from the PND. When an operator confirms a facial match, the image is passed to an investigating officer who reviews it for accuracy, and will consider all the available evidence, as they would in any normal investigation.
This is a key tool for the police to identify suspects more quickly and accurately. It can also help identify missing or deceased people, where other methods would not be appropriate or effective.
What is Operator Initiated Facial Recognition?
OIFR allows officers, after engaging with a person of interest, to photograph and check their identity on a mobile phone where they are not sure, without having to arrest them and take them into custody.
There is currently no national OIFR tool available to forces in England and Wales. The findings will inform consideration of a future national service.
What do the test results tell us?
The NPL report gives an impartial, scientifically underpinned and evidence-based analysis of the performance of the FR algorithm which will be used within the new national RFR matching service for law enforcement.
We are now able to better understand the identification performance of RFR and OIFR systems.
- There are settings the version of the IDEMIA MBSS FR algorithm selected for deployment by the Home Office can be used to deliver high search accuracy in operation using settings at which there is no significant demographic variation in performance.
- The recommended settings of the algorithm to be used in operation in the new FR service will be based upon evidence from the NPL testing and other available sources. The efficacy and equitability of the service will be monitored in use and any necessary changes to the settings nationally can be considered by policing as a matter of operational policy.
How have Policing and the Home Office responded to the results?
Public authorities have a duty under the Public Sector Equality Duty to have due regard to certain equality considerations when exercising their functions.
The results from the testing assist the Home Office and policing with further understanding of how to use FR technology fairly to prevent and detect crime, safeguard national security and keep people safe.
The findings will inform the operational settings, operator training and rollout of the new national RFR matching service for law enforcement. The findings will inform consideration of a future national OIFR service.
No decisions will be made by the algorithm. Specially trained operators will make their own decisions based on the suggestions from the RFR system. Where a match has been made, an investigating officer will follow the process for a police investigation.
The full results are presented in the NPL’s commissioned report: Facial Recognition Technology in Law Enforcement Equitability Study for Strategic Facial Matching (SFM)