Please note: The algorithm descriptions in English have been automatically translated. Errors may have been introduced in this process. For the original descriptions, go to the Dutch version of the Algorithm Register.
Document scanners for civil affairs (Facial recognition)
- Publication category
- Other algorithms
- Impact assessment
- DPIA
- Status
- In use
General information
Theme
Begin date
Contact information
Responsible use
Goal and impact
The aim of using document scanners is to improve the ability to verify whether identification documents submitted or presented are genuine. An algorithm is better able to assess the authenticity features of an identification document than a human can with the naked eye. If a document is flagged as not genuine by the algorithm, a second check is carried out, during which the details are compared with those in the BRP. Subsequently, if the document is confirmed to be genuine or if there is any doubt, its authenticity is assessed in accordance with the four-eyes principle. Ultimately, a finding that a document is not genuine may result in a report being made to the police.
Considerations
The algorithm is a tool that supports visual checks. It helps to ensure accurate identity verification without replacing human judgement.
An algorithm is better at distinguishing authenticity features than humans. Checks are always carried out by a member of staff, and the four-eyes principle is applied. If an initial check cannot guarantee authenticity, a second check is carried out, again under human supervision. The use of the algorithm reduces the risk of various forms of fraud.
Human intervention
The employee decides for themselves whether to use the facial scan and assesses the result. In case of doubt, a colleague is consulted (four-eyes principle).
Risk management
No biometric data is stored. The entire facial comparison is carried out locally within the secure municipal infrastructure; no biometric data or other data is transmitted via the internet or stored externally. The facial comparison is temporary and visible only to authorised staff. The application is standardised for all citizens and includes access controls, thereby limiting the risk of profiling or unlawful processing.
Legal basis
BRP Act, Article 2.67(4); BRP Decree, Article 35; UAVG, Article 29 – the use of biometrics is permitted where authentication is necessary.
Links to legal bases
Impact assessment
Operations
Data
A live image of the member of the public and the image from the identity document (for example, a photo on a chip or the MRZ). The member of staff can also carry out a check to verify that the passport photo matches the person at the counter.
Technical design
The algorithm has been trained to recognise which features on an identity document guarantee its authenticity. By scanning a submitted document for these features, the algorithm can determine whether the document’s authenticity can be guaranteed. If this is not the case, a secondary check is carried out by the back office, involving a more comprehensive scan using additional authenticity features and supervised by a member of staff. This ensures that authenticity can be guaranteed, even in cases where, for example, damage to the document means that authenticity cannot be verified at first instance.
The algorithm uses facial comparison based on deep learning technology. The software is integrated into the counter application and utilises underlying APIs (e.g. C++, Java, .NET, BioAPI 2.0). A comparison score is generated and no biometric data is stored. Processing takes place locally.
External provider
Similar algorithm descriptions
- A tool that assists counter staff in verifying a person’s identity by comparing the face of the person presenting themselves with the photograph on an identity document. Helps to prevent look-alike fraud.Last change on 14th of July 2026, at 6:25 (CET) | Publication Standard 1.0
- Publication category
- Other algorithms
- Impact assessment
- Field not filled in.
- Status
- In use
Facial Comparison – Tool for identity verification at the local council counter
Municipality of Vaals
A tool that assists counter staff in verifying a person’s identity by comparing the face of the person presenting themselves with the photograph on an identity document. Helps to prevent look-alike fraud.Last change on 17th of July 2026, at 6:48 (CET) | Publication Standard 1.0- Publication category
- Other algorithms
- Impact assessment
- Field not filled in.
- Status
- In use
- Tool that assists front desk staff in establishing identity by comparing the face of the person reporting to the photo on an identity document. Helps prevent look-alike fraud.Last change on 18th of September 2025, at 12:57 (CET) | Publication Standard 1.0
- Publication category
- High-Risk AI-system
- Impact assessment
- Field not filled in.
- Status
- In use
- Tool that assists front desk staff in establishing identity by comparing the face of the person reporting to the photo on an identity document. Helps prevent look-alike fraud.Last change on 26th of June 2025, at 9:59 (CET) | Publication Standard 1.0
- Publication category
- Other algorithms
- Impact assessment
- Field not filled in.
- Status
- In use
- Tool that assists front desk staff in establishing identity by comparing the face of the person reporting to the photo on an identity document. Helps prevent look-alike fraud.Last change on 3rd of November 2025, at 9:37 (CET) | Publication Standard 1.0
- Publication category
- Other algorithms
- Impact assessment
- Field not filled in.
- Status
- In use