RNI Facial Scan

Municipality of Amsterdam

Automated facial comparison during the RNI registration process. An algorithm that can help registrants prevent ‘look-alike fraud’.

Last change on 2nd of July 2026, at 15:53 (CET) | Publication Standard 1.0

• Publication category: Impactful algorithms
• Impact assessment: Field not filled in.
• Status: In use

General information

Theme

Public Order and Safety

Begin date

2022-07

Contact information

[e-mail]

Link to publication website

https://www.nederlandwereldwijd.nl/rni/contact-rni-gemeente

Responsible use

Goal and impact

The algorithm compares the face of the person at the counter with the photograph in their identity document and indicates the degree of certainty that the person in the photograph on the scanned identity document is the same person. This algorithm helps the RNI staff member at the counter to determine with greater certainty whether the person at the counter matches the person whose identity document has been scanned.

Amsterdam is one of the local authorities designated to maintain the RNI. To this end, the local authority has set up counters at a number of locations where the technology described is used.

Considerations

The use of this algorithm helps the RNI staff member to verify the identity of the member of the public at the counter.

Human intervention

Ultimately, it is the RNI staff member who decides whether to use the facial scan and what to do with the results of the facial scan as part of the process.

Risk management

There is a small risk that the processing of personal data may have a negative impact on the rights and freedoms of the data subjects. As the facial scan is not stored (the scan is only recorded in the system during the identity verification process and is visible only to staff at the RNI counter), the risk of the facial image being leaked or tampered with is low.

Legal basis

The civil servant employed by the Municipality of Amsterdam carries out the work under the responsibility of the Ministry of the Interior.

Sections of the Act:

• https://wetten.overheid.nl/jci1.3:c:BWBR0033715&chapter=2&section=2&paragraph=2&article=2.67&z=2025-02-12&g=2025-02-12
• https://wetten.overheid.nl/jci1.3:c:BWBR0034306&chapter=2&section=2&paragraph=2&article=35&z=2025-01-01&g=2025-01-01
• https://wetten.overheid.nl/jci1.3:c:BWBR0040940&hoofdstuk=3&paragraaf=3.1&artikel=29&z=2018-05-25&g=2018-05-25

Operations

Data

A photograph of the chip from the identity document shown, a photograph of the identity document itself, and the photograph taken by the facial scanner.

Technical design

Deep learning. Advanced face recognition APIs: C++, Java, Microsoft .NET, BioAPI 2.0 Verification Engine (C API). Documented examples for the main use cases and specific implementations. Tools for biometric evaluations, including the generation of ‘identification match’ summaries and ‘similarity matrix’ data.

When registering a citizen in the RNI, we use a scanning solution. This scanning solution consists of an ID scanner, an A4 scanner, a scan server, a small monitor and, since February 2021, a facial scanner. This scanning solution assists the RNI staff member in registering the applicant and, since the introduction of the facial scanner, also in verifying their identity. The details from the scanned identity document are displayed on the small monitor and, if there are no issues, the scanned data is transferred from the scanning solution to the RNI application. The data used to verify identity is not transmitted to the RNI application, but the result is displayed on the small monitor. The data from the scanned identity document is used for registration in RNI following approval by the RNI staff member. Regarding the facial scan, only a log entry is sent to RNI stating that it has been carried out and what the result was. This result may be: ‘The faces match’ or ‘The faces do not match’.

External provider

Cognitec and Thales