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.

Automated facial comparison at Civil Affairs

This algorithm assists civil affairs staff in preventing "look-alike fraud" by comparing the face of the person at the counter with the image in the scanned identity document.

Last change on 6th of May 2025, at 15:07 (CET) | Publication Standard 1.0
Publication category
Impactful algorithms
Impact assessment
DPIA
Status
In use

General information

Theme

  • International
  • Public Order and Safety

Begin date

2025-04

Contact information

info@velsen.nl

Responsible use

Goal and impact

The purpose of this algorithm is to check the identity of people registering for the first time in the BRP in the Netherlands from abroad. It compares the face of the person at the counter with the image in the scanned identity document and indicates with what certainty it is the same person. This supports the civil affairs officer in establishing identity and helps prevent "look-alike fraud".


The impact is that it increases the reliability of the BRP registration process and supports the civic affairs officer in making identity determination decisions. The facial comparison is deployed for first-time settlers from abroad and not in possession of an NL travel document with a fingerprint.

Considerations

The deployment of this algorithm helps the civil affairs officer establish the identity of the citizen at the counter. It increases the reliability of the process and reduces the risk of identity fraud. At the same time, privacy implications and the role of human decision-making in the process were carefully considered.

Human intervention

There is always human intervention. The civil affairs officer decides whether the facial scan is used and what is done with the result. The employee is ultimately responsible for the decision on identity determination and possible rejection of registration in the BRP.

Risk management

  • The facial image is recorded in the system only during the identity determination process and is visible only to civil affairs staff. This limits the risk of data leakage or manipulation. After identity is established, the facial image is not retained.
  • The performance of the system is regularly reviewed to ensure accuracy.
  • Strict access controls and security measures are implemented to prevent unauthorised access to the system.
  • Employees are and have been trained in using the system and in recognising potential errors or limitations.

Legal basis

  • BRP Act art. 2.67 4th paragraph: Legal obligation to establish proper identity
  • BRP Decree art.35
  • UAVG art. 29: Admissibility of biometrics for authentication

Elaboration on impact assessments

A DPIA has been carried out on the use of Oribi.

Impact assessment

Data Protection Impact Assessment (DPIA)

Operations

Data

The system uses:

  • Face scan of the person at the counter
  • Scanned image from the identity document

Technical design

The system uses deep learning and advanced facial recognition APIs. Technical components include:

  • ID scanner/A4 scanner
  • Scan server
  • Facial scanner (face camera)

The process is as follows:

1. The identity document is scanned.

2. A face scan is made of the person at the counter.

3. The algorithm compares the facial scan with the image from the identity document.

4. The result of the comparison is displayed on the civil affairs officer's screen.

5. The civil affairs officer evaluates the result and makes a decision.

Only the result of the scan ('The faces are the same' or 'The faces are not the same') is written down anonymously in a file to track the effectiveness of the algorithm. Individual results are not stored. For the outcome 'The faces are not the same', the usual procedure is deployed for the use of potentially false documents.


NB. Document scanner is also used. The document is checked for authenticity. The face scan may give a "good" result, but the document may still be confiscated because it is not classified as genuine by the document scanner. The usual procedure is also used for this.

External provider

ORIBI-ID solutions (www.oribi.nl)

Similar algorithm descriptions

  • This algorithm supports BRP employees in preventing "look-alike fraud" by comparing the face of the person at the counter with the image in the scanned identity document.

    Last change on 8th of May 2025, at 8:24 (CET) | Publication Standard 1.0
    Publication category
    Impactful algorithms
    Impact assessment
    Field not filled in.
    Status
    In use
  • This algorithm supports BRP employees in preventing "look-alike fraud" by comparing the face of the person at the counter with the image in the scanned identity document.

    Last change on 14th of January 2025, at 10:43 (CET) | Publication Standard 1.0
    Publication category
    Impactful algorithms
    Impact assessment
    Field not filled in.
    Status
    In use
  • This algorithm supports BRP employees in preventing "look-alike fraud" by comparing the face of the person at the counter with the image in the scanned identity document.

    Last change on 3rd of December 2024, at 7:30 (CET) | Publication Standard 1.0
    Publication category
    Impactful algorithms
    Impact assessment
    Field not filled in.
    Status
    In use
  • This algorithm supports RNI staff in preventing "look-alike fraud" by comparing the face of the person at the counter with the image in the scanned identity document.

    Last change on 1st of November 2024, at 16:51 (CET) | Publication Standard 1.0
    Publication category
    Impactful algorithms
    Impact assessment
    Field not filled in.
    Status
    In use
  • Automated facial comparison for first registration in the Basic Registry of Persons (BRP), resettlement applications and naturalisation applications for persons over 18 years old. This algorithm helps the registrant prevent "look-alike fraud". Sourced from the Rijksdienst voor Identiteitsgegevens (RvIG).

    Last change on 20th of August 2024, at 7:18 (CET) | Publication Standard 1.0
    Publication category
    Impactful algorithms
    Impact assessment
    Field not filled in.
    Status
    In use