Document Layout Interpretation and its Applications
This site provides a central repository of information, source code, demos and datasets for researchers in the field of document layout interpretation. This page is a new resource, and will continue to evolve and expand in the near future. If you would like to have a link to your page from this site, please email Andrew Bagdanov.
While this site acts as a repository of information, the DLIA eGroup
is an active forum for open discussion of current research topics.
If you are interested in document layout interpretation, please consider
joining and participating in the DLIA eGroup. You can join the discussion
list by entering you email address in the form below:
Research Groups
Document Image Analysis
and Understanding Group at LACAM
Language and Media
Processing (LAMP) group at UMD
Center of Excellence
for Document Analysis and Recognition (CEDAR) at Buffalo University
Document Analysis
and Media Processing Team, University of Oulu, Finland
Writing REcognition
and Analysis of Documents (READ) group at LORIA
Document Analysis at DFKI
Document ANalysis
and TEchnologies research group (DANTE) at the Universities of Firenze
and Siena, Italy
CENPARMI: Centre
for Pattern Recognition and Machine Intelligence at Concordia University
Intelligent Systems
Laboratory at the University of Washington
OCR
and Text Recognition Group at ITC-irst, Italy
The CODICE Project
at ITC-irst, Italy
Conferences, Calls for Papers and Special Issues
CAMP2000
CISST2000
Online
Proceedings of DLIA99
15th ICPR
Datasets
University
of Oulu Document Database
UW-I
English Document Image Database
UW-II
English/Japanese Document Image Database
UW-III
English/Technical Document Image Database
Software
Voronoi
segmentation tools from Kise, et al
WISDOM++ from LACAM
Bibliographies
DOCBIB (bibliography
of document image understanding)
USC
Annotated Computer Vision Bibliography
GLIMPSE Collection
of Computer Science Bibliographies
General
Document Understanding
Web Server at the University of Maryland
XML Information at w3.org