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 document verification and facial recognition.
- Publication category
- High-Risk AI-system
- Impact assessment
- Field not filled in.
- Status
- In use
General information
Theme
Begin date
Contact information
Responsible use
Goal and impact
The automated document check and facial recognition system serve three purposes, namely: 1. Verifying the identity of the applicant for an identity document in order to prevent identity fraud; 2. To verify the authenticity of the source documents provided from the country of origin in order to prevent forgery; 3. To ensure the reliability of the information held in the Basic Register of Persons (BRP).
If the applications, using the algorithm, indicate that the person whose identity document and face have been scanned is not the person standing at the counter, the Public Services counter staff member will call in a colleague to verify this finding. A number of applications are processed by foreign affairs specialists. These specialists also apply the ‘four-eyes principle’ in cases of doubt regarding the findings of the document and/or facial scan. If they conclude that the result of the document check and/or facial comparison is correct and the applicant’s identity does not match the identity on the source documents and/or photograph, the application for registration in the BRP or for an identity document will be rejected. In the event of such a rejection, it may be indicated whether there is a suspicion of fraud. In that case, the Police and/or the Military Police are called in for further investigation.
Considerations
The use of this algorithm helps staff in the Public Services Department to verify the identity of members of the public at the counter. Documents contain a number of security features that the document scanner can detect more accurately than the human eye. This also applies to the verification of biometric features in the face.
Human intervention
Yes. No distinction is made in the use of the document scanner and facial recognition system. Both tools are used for every citizen who comes to register as a resident of the municipality of 's-Hertogenbosch and/or to apply for identity documents. Furthermore, the ‘four-eyes principle’ is applied if the result of the document check or facial recognition check is negative. Finally, a final check is also carried out by a counter clerk when identity documents are issued.
Risk management
By always using the applications when registering with the BRP or when applying for identity documents, the risk of potential profiling is ruled out from the outset. A further risk is that the automated document check or facial recognition system could lead to an automated decision. This risk is mitigated by ensuring that the findings are always reviewed by a member of staff. In cases of doubt, this review is carried out by at least two members of staff.
Legal basis
Legal obligation to carry out proper identity verification: BRP Act, Article 2.67(4); BRP Decree, Article 35. Admissibility of biometrics: UAVG, Article 29; in the present situation, authentication is necessary.
Links to legal bases
Operations
Data
Biometric features on the face and security features on the document.
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.
External provider
Similar algorithm descriptions
- Algorithm that can help registrants avoid "look-alike fraud". Sourced from the National Authority for Identity Data (RvIG)Last change on 16th of August 2024, at 9:46 (CET) | Publication Standard 1.0
- Publication category
- High-Risk AI-system
- Impact assessment
- Field not filled in.
- Status
- In use
- Automated document check and facial comparison for registrations in the BRP, applications for travel documents and driving licences, and for reporting removals (intra-municipal and migrations). The tool checks the authenticity characteristics of identity documents and prevents "look-alike fraud".Last change on 1st of May 2025, at 12:11 (CET) | Publication Standard 1.0
- Publication category
- Impactful algorithms
- Impact assessment
- Field not filled in.
- Status
- In use
- Algorithm that can help registrants avoid "look-alike fraud".Last change on 28th of July 2025, at 11:20 (CET) | Publication Standard 1.0
- Publication category
- Other algorithms
- Impact assessment
- DPIA
- Status
- In use
- Automated facial comparison and document check during first registration in the Basic Registry of Persons (BRP), resettlement applications and naturalisation applications for persons over 18 years old. This algorithm supports the BRP employee to prevent "look-alike fraud" and check authenticity of a document.Last change on 8th of May 2025, at 11:13 (CET) | Publication Standard 1.0
- Publication category
- Impactful algorithms
- Impact assessment
- Field not filled in.
- Status
- In use
- Automated facial comparison in the RNI registration process. Algorithm that can help registrants avoid "look-alike fraud".Last change on 10th of September 2025, at 15:04 (CET) | Publication Standard 1.0
- Publication category
- Impactful algorithms
- Impact assessment
- Field not filled in.
- Status
- In use