Launch of the Europeana Newspapers project

13/09/2012
Printer-friendly versionNosūtīt
Europeana Newspapers
Europeana Newspapers
1

A group of 17 European partner institutions have joined forces in the "Europeana Newspapers" project to, over the next 3 years, provide more than 18 million newspaper pages to the online service Europeana. Europeana is a single access point to millions of digitised books, paintings, films, museum objects and archival records sourced from throughout Europe.

The Europeana Newspapers project is funded under the Competitiveness and Innovation Framework Program 2007-2013 of the European Commission with the aim of aggregation and refinement of newspaper content through The European Library.

Each library participating in the project will distribute digitised newspapers and full-text via Europeana. The project aims to make the newspaper content directly accessible for users through a special interface within the content browser. This will be integrated into the Europeana portal and will allow queries of phrases or single words within the newspapers’ texts. This goes far beyond the standard libraries catalogue search functions which usually allow the searching by date or title only.

The project addresses challenges linked with digitised newspapers such as Optical Character Recognition (OCR), Optical Layout Recognition (OLR), article segmentation and page class recognition, and named entity recognition (NER). OCR is the electronic conversion of scanned images of handwritten, typewritten or printed text into machine-encoded text. OLR is concerned with the detection and separation of articles on a scanned page with more than one article. NER seeks to locate entities in the full text and to classify them according to standardised names for persons,
locations, and organisations.

The project will also evaluate the quality of the refinement technologies and transform the local metadata into the Europeana Data Model standard in close collaboration with stakeholders from
the public and private sector.

The Europeana Newspapers project is co-ordinated by the Staatsbibliothek zu Berlin – Preußischer Kulturbesitz. Follow the advancements of the Europeana Newspapers project at www.europeana-newspapers.eu. For any further information please contact Hans-Jörg Lieder or Thorsten Siegmann at Staatsbibliothek zu Berlin via info@europeana-newspapers.eu.

Project Partners:

Berlin State Library National   Library of the Netherlands
National Library of Estonia   Austrian National Library
University of Helsinki, National Library of Finland   Hamburg State and University Library
National Library of France   National Library of Poland
CCS Content Conversion Specialists GmbH   LIBER Foundation
National Library of Latvia   National Library of Turkey
University of Beograd   University of Innsbruck
Dr. Friedrich Tessmann Library   The British Library
University of Salford   The European Library

Europeana in a nutshell

Europeana www.europeana.eu is a multi-lingual online collection of millions of digitized items from European museums, libraries, archives and audiovisual collections. Currently Europeana gives integrated access to 23 million books, films, paintings, museum objects and archival documents from some 2.200 content providers from across Europe.