H-DIBCO 2018

ICFHR 2018 Handwritten Document Image Binarization COmpetition

Document image binarization is an important step in the document image analysis and recognition pipeline. In this respect, it is imperative to have a benchmarking dataset along with an objective evaluation methodology to capture the efficiency of current document image binarization methodologies. Following the success of DIBCO & H-DIBCO series ( DIBCO 2009 , DIBCO 2011, DIBCO 2013, DIBCO 2017, H-DIBCO 2010, H-DIBCO 2012, H-DIBCO 2014 H-DIBCO 2016) organised in conjunction with ICDAR’09, ICDAR’11, ICDAR’13, ICDAR’17, ICFHR 2010, ICFHR 2012, ICFHR 2014 and ICFHR 2016, respectively, the follow-up of this contest (H-DIBCO 2018) aims to be organised in conjunction with ICFHR 2018.

In H-DIBCO 2018, the general objective is to record recent advances in document image binarization using established evaluation performance measures. The benchmarking dataset that will be used in the contest will augment the existing dataset of the DIBCO series containing handwritten document images that are representative of the potential problems which are challenging in the binarization process.

All researchers in the field of Document Image Binarization are invited to register for participating in H-DIBCO 2018. The description of the methods and the evaluation scores will be presented during a dedicated ICFHR 2018 session. A report on the competition will be published in the ICFHR 2018 conference proceedings. At the end of the competition, the testing dataset along with the required program to run the evaluation measures will become publicly available.

NOTE : You may participate in this contest even if you do not plan to attend the ICFHR 2018 conference.

Important Dates:

  • 29 Jan. 2018 - Competition opens to the participants
  • 27 Apr. 2018
  • 10 Apr. 2018 - Deadline for registration to the contest
  • 30 Apr. 2018
  • 27 Apr. 2018 - Deadline for submission of the required executable as well as a description of the participant's handwritten document image binarization methodology.
  • 01 Jun. 2018 - Full paper submission describing the contest and the obtained results.
  • 08 August. 2018 - Final contest results to be announced at the ICFHR 2018. A report on the competition will be published in the ICFHR 2018 conference proceedings. The testing dataset will become available to the research community.


1Visual Computing Group,
Department of Electrical and Computer Engineering,
Democritus University of Thrace.

2Institute of Informatics and Telecommunications,
NCSR "Demokritos".

Resources - Evaluation

Evaluation Protocol:

All registered participants are required to submit one executable:

Binarize arg1 arg2
arg1: Input gray scale or color image
arg2: Resulting binary image

The evaluation methodology will be based upon the latest DIBCO contest, i.e. h-DIBCO 2014.
The results will become publicly available at the end of the ICFHR 2018 conference.

Want to participate? Send an e-mail!

with subject: H-DIBCO 2018 in the registration e-mail, please add affiliation and contact details.