Workshop on Text Recognition
Published: 2018-11-27
Seminar on "Automated Registration of Historical Population Registers: New Prospects and Possibilities"
Date: February 14, 2019
Location: School of Economics and Management, Building Alfa 1, room 1104
A seminar on "Automated Registration of Historical Population Registers: New Prospects and Possibilities"
Organized by the Centre for Economic Demography, Lund University, and the National Archives (Lund) in collaboration with the IUSSP Scientific Panel on Historical Demography, SwedPop, and the LONGPOP project.
Program
Welcome and introduction: Martin Dribe (Centre for Economic Demography, Lund University)
10.00-11.00 Lars Björk and Torsten Johansson, National Library of Sweden (KB), Sweden:
“Improving the OCR-process – Experiences from the newspaper digitization at the National Library of Sweden”
11.00-12.00 Anders Hast, Centre for Image Analysis (CBA), Uppsala University, Sweden:
“Making document collections searchable and readable by using handwritten text recognition techniques – possibilities and limitations”
12.00-13.00 Lunch
13.00-14.00 Peter Sandholt Jensen and Emil Nørmark Sørensen, University of Southern Denmark (SDU), Odense, Denmark:
“Digitizing and analyzing historical documents at scale: The power of AI”
14.00-15.00 Joana Maria Pujades Mora, Autonomous University of Barcelona (UAB) Barcelona, Spain:
“The big data of the past: a journey through historical population documents driven by Computer Vision”
15.00-15.30 Coffee
15.30-16.30 Panel discussion: The prospects of automatic text recognition in large scale registration of population data. Members of the SwedPop team and presenters