Grant for ICT Innovation Project
|06 February 2024
Professors Abe de Jong and Herman de Jong received a grant of 160,000 euro for a UG ICT Innovation Fund Proposal titled Digitization of printed registries to structured data. The project’s idea is to deliver a machine learning-powered online platform to extract structured information from scanned source material. The tool will be able to handle data published as printed registries, e.g. securities, trade statistics, population and production censuses, patent data etc. to enable research on such data. These sources can easily cover tens of thousands of pages. Currently, scanned or digitized versions may be obtained using existing OCR tools. But they often give scanned information as unstructured text or as paragraphs ill-suited for interpretation in the form as tables or statistics. The proposed tool will instead produce output as ordered spreadsheet data of ready-for-research output. The project will be developed together with colleagues from the UG CIT.