Optimizing the Digitization Workflow of Heritage Institutions to Increase Quality of Digitized Texts

Abstract

An often used method in digitizing heritage collections is the use of mass digitization. While this leads to a lot of digitized content in a short amount of time, quality control and information about the quality of digitized material is generally lacking. To overcome this problem, we propose a theoretical design of an optimized digitization workflow. It will be designed as a plug-in pipeline where different modules can be added or removed based on organizational needs. By integrating a high level of automation it will be suitable for high-throughput, low-funding settings.