Since the mid-1990s we have been advising a number of organisations and our software is in use in industry.
We carry out real-world research in document digitisation, character recognition (OCR) and other image analysis applications.
Ongoing and completed projects, from processing and recognition of historical books and newspapers to the analysis of web documents.
We develop and make available a number of document analysis tools, ranging from ground truth production to performance evaluation.
We have created several publicly-available datasets, ranging from historical books and newspapers to contemporary documents.
We have created and maintain PAGE, an XML-based representation framework for document analysis and recognition results.
DAS2016 on Santorini, Greece
(18/04/2016) Read more »
Turning Text Soup into Smart Data in Newspaper and Magazine Archives
(17/02/2016) Read more »
Stefan Pletschacher elected to the ALTO Editorial Board
(29/01/2016) Read more »
(08/10/2015) Read more »
ICDAR2015 Competitions – Evaluation Set
(09/03/2015) Read more »
ICDAR2015 Competitions – Registration Open
(22/01/2015) Read more »