The following list of competitions are being organized in the framework of ICDAR to evaluate the performance
of different algorithms for a number of document analysis tasks.
The results of these competitions will be presented during a specific
session during the conference.
The ICDAR 2009 Arabic Handwriting
Recognition Competition aims to bring together researchers
working on Arabic handwriting recognition. This competition
is the third in a series of competitions to establish the
state of the art of recognizing Arabic handwritten words.
(more...)
Winner:
Alex Graves Technische Universität München, Germany
The general objective of the
ICDAR2009 Handwriting Segmentation Contest is to use well
established evaluation practices and procedures in order to
record recent advances in off-line handwriting segmentation.
(more...)
Winner:
Z. Shi, S. Setlur and V. Govindaraju
Center for Unified Biometrics and Sensors (CUBS) University at Buffalo, SUNY, New York, USA
(text line segmentation)
Winner:
V. Papavassiliou, T. Stafylakis, V. Katsouros and G. Carayannis
Institute for Language and Speech Processing (ILSP),
Athens, Greece
In this first international document image
binarization contest, the general objective is to record recent
advances in document image binarization using established
evaluation performance measures. (more...)
Winner:
S.Lu, C.L. Tan
Institute for Infocomm Research, Singapore
The aim of the first ICDAR Structure Extraction
competition is to test automatic techniques to build hyperlinked
table of contents (ToC) for digitized books of diverse genre.
(more...)
Winner:
Aleksandar Uzelac
Microsoft Development Center Serbia
The aim of ICDAR2009 Handwritten Farsi/Arabic
Character Recognition Competition is to bring together researchers
working on this field. By benchmarking the state of the art
Arabic character recognition techniques on large-scale dataset,
a comparative result can be obtained. (more...)
Winner:
Alex Graves Technische Universität München, Germany
The ICDAR 2009 Online Arabic Handwriting Recognition
Competition aims to contribute in the evolution of Arabic
handwriting recognition research. This competition will be
organized on the new database on online Arabic handwritten
text (ADAB). (more...)
Winner:
Zsolt Wimmer and Pierre-Michel Lallican
Vision Objects, SA, France
The goal of the proposed competition is
to evaluate automatic handwriting recognition systems on snippets
of French words with the help of given dictionaries of different
sizes (e.g. 100 and 2000 words). (more
...)
Winner:
Alex Graves Technische Universität München, Germany
To give academia and industry the opportunity
to test their systems (online, offline or combined), we provide
new unpublished forensic-like signature datasets. These sets
contain both on- and offline authentic signatures and skilled
forgeries in multiple formats. (more
...)
Winner:
A. Filatov, I. Kil, T. Strunkov
Parascript LLC, USA
(online)
Winner:
A. Hassaïne, E. Decencière
Centre de Morphologie Mathématique, France
(offline)
Winner:
F. Alonso-Fernandez, M. Martinez-Diaz, J. Fierrez, J. Ortega-Garcia
Biometric Recognition Group - ATVS Universidad Autonoma de Madrid, Spain
Page Segmentation is of fundamental importance
among Layout Analysis steps and has been (and continues to
be) relatively well researched. The motivation of the competition
is to evaluate existing approaches using a realistic dataset
and an objective performance analysis system. (more
...)
Winner:
Iuliu Konya, Stefan Eickeler, Christoph Seibert
Fraunhofer Institute for Intelligent Analysis and Information Systems
Sankt Augustin, Germany