This article details the work undertaken by the National Library of Australia Newspaper Digitisation Program on identifying and testing solutions to improve OCR accuracy in large scale newspaper digitisation programs. In 2007 and 2008 several different solutions were identified, applied and tested on digitised material now available in the Australian Newspapers Digitisation Program beta service <http://ndpbeta.nla.gov.au/ndp/del/home>. This article gives a state of the art overview of how OCR software works on newspapers, factors that effect OCR accuracy, methods of measuring accuracy, methods of improving accuracy, and testing methods and results for specific solutions that were considered viable for large scale text digitisation projects.
The <div> TYPE attribute vocabulary is a list of terms that may be used to categorise the core structural elements of an object in a METS document conforming to the Australian METS Profile. Examples of how these values may be applied are given in the Appendix – Content Models. The content model in the current version of the document represent use cases that have been tested by the Maintenance Agency, and further content models and vocabulary terms will be added as they are developed.
This report contains the results of the PRESTA - PREMIS Requirements Statement project undertaken by the National Library of Australia from December 2005 to June 2006 for the Australian Partnership for Sustainable Repositories (APSR).
The National Library of Australia, in collaboration the Australian State and Territory libraries, has commenced a
program to digitise out of copyright newspapers.