Creating a Complete Workflow for Digitising Historical Census Documents
Christian Clausner, Justin Hayes, Apostolos Antonacopoulos, Stefan Pletschacher · 2017
The 1961 Census of England and Wales was the first UK census to make use of computers. However, only bound volumes and microfilm copies of printouts remain, locking a wealth of information in a form that is practically unusable for research. In this paper, we describe process of creating the digitisation workflow that was developed as part of a pilot study for the Office for National Statistics. The emphasis of the paper is on the issues originating from the historical nature of the material and how they were resolved. The steps described include image pre-processing, OCR setup, table recognition, post-processing, data ingestion, crowdsourcing, and quality assurance. Evaluation methods and results are presented for all steps.