IMProving ACcess to Text - Project details (IMPACT)

Text that is not digital is virtually invisible. Today’s readers search the internet for electronically accessible texts rather than visit the reading room of a library. Born-digital and digitised contemporary materials contain the richness that allows tools such as text mining and the semantic web to offer superior accessibility but the story is very different for historic documents. A vital part of the European heritage, encompassing more than four centuries of historic books and bound periodicals is becoming less and less visible to the public at large.
With the i2010 vision of a European Digital Library, the EU has launched an ambitious plan for large scale digitisation projects transforming Europe’s printed heritage into digitally available resources. However, lack of institutional knowledge and expertise slows down the pace with which this vision can be realised. The state-of-the-art in OCR performance and machine understanding of the original document is inadequate, especially for historically important material with archaic fonts and spellings, newspapers with complex layouts, bound volumes, microfilm or typescript. The IMPACT project will remove many of these barriers. It brings together fifteen national and regional libraries, research institutions and commercial suppliers - all centres of competence with unequalled experience of large-scale text digitisation processes and technologies. The project will let them share their know-how and best practices, develop innovative tools to enhance the capabilities of OCR engines and the accessibility of digitised text and lay down the foundations for the mass-digitisation programmes that will take place over the next decade. This project will facilitate a more collaborative approach to mass-digitisation. It will build capacity and lower the barriers to entry for organisations in the early stages of their own digitisation activity.



Project board at the SUB Göttingen

Project staff at the SUB Göttingen

SUB Göttingen departments / units involved in the project

Former project staff of the SUB Göttingen

Mohamed Abergna, Dennis Neumann