Document image binarization is an important step in the document image analysis and recognition pipeline. Therefore, it is imperative to have a benchmarking dataset along with an objective evaluation methodology in order to capture the efficiency of current document image binarization practices. Following the success of DIBCO 2009 organized in conjunction with ICDAR’09 as well as of H-DIBCO 2010 organized in conjunction with ICFHR 2010, the follow-up of these contests in the framework of ICDAR 2011 is organized. The general objective of DIBCO 2011 is to record recent advances in document image binarization using established evaluation performance measures and a benchmarking dataset that is representative of the potential challenges met in the binarization process.
The DIBCO 2011 dataset will contain images that range from gray scale to color and from machine printed to handwritten. For the preparation of the participants using the new dataset, the existing publicly available datasets of previous contests (DIBCO 2009 and H-DIBCO 2010) along with the corresponding ground truth could be used.
We invite all researchers in the field of Document Image Binarization to register for participating in DIBCO 2011. An agreement will be signed by the participants and the organizers in order to protect the Intellectual Property Rights (IPR) of the submitted software. The description of the methods and the evaluation scores will be presented during a dedicated ICDAR 2011 session. A report on the competition will be published in the ICDAR 2011 conference proceedings.
Note: You may participate in this contest even if you do not plan to attend the ICDAR 2011 conference.
1Democritus University of Thrace, Greece
2National Center for Scientific Research "Demokritos", Greece
see Table with DIBCO 2011 FINAL RESULTS !!!