Building and maintaining a national resource to support critical research and development in translation, document analysis, preservation, and exploitation.
In order to get an account and access the contents of this website and its resources, please contact the administrator directly. If you actually know what this platform is and what it was designed for, you should quite easily know who to contact.
DAE now has its own tweet: http://twitter.com/daeplatform.
This contest aims to provide a metric giving indications on the influence of individual specific document analysis tools to overall end-to-end applications. Contestants are provided with a full, working pipeline operating on a raw document page image and proceeding to extract some final information. The pipeline is built with clearly identified analysis stages (e.g. binarization, skew detection, layout analysis, OCR ...) that have a formalized input and output. Contestants are invited to contribute their own algorithms as an alternative to one or more of the initially provided stages and evaluation will be done on the overall impact of the contributed algorithm to the final (end of pipeline) result.
All the source code powering this web site, as well as other software tools (related to data import, conversion from other data sources etc.) are now available under GPL from Sourceforge. Feel free to contribute !
If you are reading this message, there is a very high chance you are, or have just been, participating to the DAS 2010 workshop in Boston, where our platform was officially and publically launched.
The DAE project platform will be demonstrated at the 2010 DAS Worksop in Boston. It will be illustrated by a poster. which is attached here.
The DAE project will be show cased at the Ninth IAPR International Workshop on Document Analysis Systems June 9th-11th, 2010 in Boston, MA, USA. Check the attachment for demo description (authenticated users only).