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 search
- Publication category
- Other algorithms
- Impact assessment
- DPIA
- Status
- In use
General information
Theme
Begin date
Contact information
Link to publication website
Responsible use
Goal and impact
The purpose of using algorithms is to speed up the verification of authenticity and formatting and issue of source documents. These algorithms support document experts by indicating if there are discrepancies. Another purpose is for keeping notes on the source documents checked and making the process easier by viewing comparables.
Considerations
Document experts face a very high workload and limited capacity. Using multiple algorithms, the experts can see faster whether a source document is genuine and has been obtained correctly. Thus, the document expert can do the authenticity check faster.
Human intervention
The algorithms learn from annotations made by document experts in scanned source documents. It provides an initial judgement. This means that the algorithms support the document research of the document experts. The final decision always lies with the document experts.
Risk management
The document experts perform sampling on source documents and assess whether, for example, the algorithm has correctly recognised the source document by document type and country name. If the algorithm makes a wrong decision, this is manually reversed by the document experts. Even source documents that have been recognised correctly by the algorithm are still examined manually using a random sample. The document experts always remain responsible for the final decision.
Legal basis
- Articles 14, 20, 28, 33 and 45a of the Aliens Act stipulate that the Minister is authorised to grant, amend and/or revoke residence permits.
- Article 3:2 of the General Administrative Law Act stipulates that, when preparing a decision, the administrative body must obtain the necessary knowledge of the relevant facts and interests to be weighed up. An obligation to conduct an investigation, therefore.
Links to legal bases
- Artikel 14 Vreemdelingenwet: https://wetten.overheid.nl/jci1.3:c:BWBR0011823&hoofdstuk=3&afdeling=3¶graaf=1&artikel=14&z=2024-01-01&g=2024-01-01
- Artikel 20 Vreemdelingenwet: https://wetten.overheid.nl/jci1.3:c:BWBR0011823&hoofdstuk=3&afdeling=3¶graaf=2&artikel=20&z=2024-01-01&g=2024-01-01
- Artikel 28 Vreemdelingenwet: https://wetten.overheid.nl/jci1.3:c:BWBR0011823&hoofdstuk=3&afdeling=4¶graaf=1&artikel=28&z=2024-01-01&g=2024-01-01
- Artikel 33 Vreemdelingenwet: https://wetten.overheid.nl/jci1.3:c:BWBR0011823&hoofdstuk=3&afdeling=4¶graaf=2&artikel=33&z=2024-01-01&g=2024-01-01
- Artikel 45a Vreemdelingenwet: https://wetten.overheid.nl/jci1.3:c:BWBR0011823&hoofdstuk=3&afdeling=5¶graaf=1&artikel=45a&z=2024-01-01&g=2024-01-01
- Artikel 3:2 Algemene wet bestuursrecht: https://wetten.overheid.nl/jci1.3:c:BWBR0005537&hoofdstuk=3&afdeling=3.2&artikel=3:2&z=2024-05-01&g=2024-05-01
Elaboration on impact assessments
DPIA has been carried out
Impact assessment
Operations
Data
High-quality digital scans of source documents and human annotations. Such as country, document type and, whether two details are the same. Document experts review the new information and make new annotations. After checking these annotations, this is added to the data. As a result, the algorithms work better and better. The algorithms keep learning about patterns in the data based on feedback from the document experts.
Technical design
Based on source document data, a VGG16 neural network is trained on features of document data. If there is a substantial part of a particular document, it will be included in the train set. This allows, for example, the document type and document details, such as colour and shapes, to be recognised.
The source documents are scanned and presented to the system. The scan is also presented to the neural network. The response is captured automatically. If the offered source document is in order, a positive decision is made on the source document.
External provider
Similar algorithm descriptions
- At the civil affairs counter, old documents submitted for replacement for a new, valid one must be scanned for authenticity. The document scanner scans the authenticity characteristics of a driving licence, identity card or passport. If authenticity is established, the resident will receive a new document.Last change on 23rd of January 2025, at 15:52 (CET) | Publication Standard 1.0
- Publication category
- Impactful algorithms
- Impact assessment
- DPIA
- Status
- In use
- The algorithm underlines personal data in documents. An employee has to review all the pages and check whether the document is properly anonymised. Then the software removes all highlighted information and blacklists it. After that, the documents can be published, for example under the Open Government Act.Last change on 19th of September 2024, at 9:10 (CET) | Publication Standard 1.0
- Publication category
- Other algorithms
- Impact assessment
- DPIA, ...
- Status
- In use
- The algorithm underlines personal data in documents. An employee has to review all the pages and check whether the document is properly anonymised. Then the software removes all highlighted information and blacklists it. After that, the documents can be published, for example under the Open Government Act.Last change on 18th of June 2024, at 8:38 (CET) | Publication Standard 1.0
- Publication category
- Other algorithms
- Impact assessment
- DPIA, ...
- Status
- In use
- The algorithm underlines personal data in documents. An employee has to review all the pages and check whether the document is properly anonymised. Then the software removes all highlighted information and blacklists it. After that, the documents can be published, for example under the Open Government Act.Last change on 17th of June 2024, at 10:40 (CET) | Publication Standard 1.0
- Publication category
- Other algorithms
- Impact assessment
- Field not filled in.
- Status
- In use
- The algorithm underlines personal data in documents. An employee has to review all the pages and check whether the document is properly anonymised. Then the software removes all highlighted information and blacklists it. After that, the documents can be published, for example under the Open Government Act.Last change on 8th of July 2024, at 15:45 (CET) | Publication Standard 1.0
- Publication category
- Other algorithms
- Impact assessment
- Field not filled in.
- Status
- In use