In the fourth episode of the interview series ‘The people of TRIADO’, Rutger van Koert, software developer at the Digital Infrastructure department of the KNAW Humanities Cluster, is speaking. Watch the interview with Rutger van Koert on YouTube.
From source to digitally readable text
At TRIADO Van Koert assists in converting the written and / or printed source material from the CABR into a digitally readable text. In addition, he is responsible for automatically classifying those digitized documents from CABR. He also enriches those documents with metadata. This is done using advanced software that recognizes and classifies names, titles, organizations and dates in the current text.
At the KNAW Humanities Cluster, Van Koert is responsible, among other things, for digital image analysis in the research project ‘Digital Forensics’ at Huygens ING. In addition, Van Koert is responsible for the software that can classify elements from early modern and medieval manuscripts. This is incredibly complicated: the further back in time a text is written down, the harder it becomes to identify the script. Finally, Van Koert provides software which looks at a scan of a medieval manuscript and determines whether it is the main text body or marginal texts. This means that he can have these texts saved separately.
Researchers save time
According to Van Koert, researchers will soon be able to extract interesting research data from the archives and compare them with information from other archives, thanks to the methods tested in TRIADO. By unlocking archives completely digitally, you will soon get the results you want at the touch of a button, instead of having to do years of archival research. If the method now being developed in the TRIADO project works well and is optimized as much as possible, then the chances are that this method will also work for other archives. Van Koert: ‘What makes this project so special is the scale on which we are now testing. We are now testing these methods with a set of hundreds of thousands of scans instead of several hundred.’
People of TRIADO
In the interview series ‘The people of TRIADO’, the people involved in the project Tribunal archives as digital research facility are interviewed. They tell about their expertise and role in the project. But also about their expectations and the importance of TRIADO. In total, about 10 people are interviewed. Marten Düring, member of the scientific advisory committee. Marian Hellema, initiator of a digitization workflow, Anne Gorter, project manager Nationaal Archief and Rutger van Koert, software developer at the Digital Infrastructure department of the KNAW Humanities Cluster, have been interviewed.
With TRIADO (Tribunal archives as a digital research facility), the most frequently consulted Second World War Archives of the Netherlands, the Centraal Archief Bijzondere Rechtpleging (CABR), are made digitally more searchable. TRIADO is a project of Netwerk Oorlogsbronnen, Huygens ING (KNAW) and the Nationaal Archief. The project runs until July 2019. In the research project, TRIADO aims to develop an efficient and effective methodology that can convert large quantities of unstructured, analogue data from archival collections into usable digital research data. The sector, researchers and other interested parties can follow this process via the interview series ‘The people of TRIADO’. Several employees of the Tribunal archives project as a digital research facility (TRIADO) talk about their expertise and role in the project.