Keynote presentation given at the Swedish Symposium on Image Analysis 2010 (SSBA2010), Uppsala, Sweden, March 11-12, 2010
This paper outlines the challenges and opportunities in large-scale analysis and recognition of scanned historical documents. After a brief overview of the background of large-scale digitisation and its overall challenges, the characteristics of the documents and the artefacts encountered are presented according to how they occur throughout the lifecycle of a document. The stages of full-text digitization are presented next, with an emphasis on the document image analysis pipeline. The paper ends with some pointers to past and current notable digitization research initiatives.
A. Antonacopoulos , "Large-Scale Digitisation and Recognition of Opportunities for Image Processing and Analysis Historical Documents: Challenges and Analysis", Keynote presentation given at the Swedish Symposium on Image Analysis 2010 (SSBA2010), Uppsala, Sweden, March 11-12, 2010