"The Robust Reading Competition has moved to its new permanent space at http://rrc.cvc.uab.es. This site will remain available but will not accept any further submissions from January 2015 onwards. Please use the new site at http://rrc.cvc.uab.es for up to date information and to submit new results. You can continue to use your existing user accounts while all associated data have been transferred to the new site. If you encounter any problem, please contact us. Apologies for any inconvenience caused."

Introduction

Given the high interest demonstrated during the ICDAR 2011 Robust Reading Competition (36 submissions over 2 challenges) [2,3] and the increasing interest of the community on complex text containers, the ICDAR 2013 Robust Reading Competition revisits the past two challenges on static real scene images and born-digital images, and introduces a brand new challenge on video data.

Each challenge is organised around different tasks, covering key steps in the text extraction process such as text localisation, pixel-level segmentation and recognition. We have strived to structure all challenges in a similar way in order to facilitate the participation to multiple challenges.

The first phase of the ICDAR 2013 Robust Reading Competition tool place between January and April 2013, and the results were presented during the International Conference on Document Analysis and Recognition (ICDAR) 2013 that took place in Washington DC, USA, in August 2013 [1].

During the first phase of the competition, 52 submissions were received (42 if variants of the same method are excluded) over the different challenges offered by the competition. The results per Challenge can be consulted in the corresponding section of this Web site.

Since ICDAR 2013, the competition has entered its second phase, where researchers can submit new results for evaluation at any date in a continuous mode. The competition site provides on-line evaluation of submitted results and tools for visualisation and comparison to other submitted methods. The researchers can opt to make their obtained results public or just use the comparison functionality of the Web site in a private way.

During the first six months of this second phase, the competition Web site was visited by more than 2500 unique visitors, and has over 300 registered users who have made more than 1,000 (private) submissions of new results.

  1. D. Karatzas, F. Shafait, S. Uchida, M. Iwamura, L. Gomez, S. Robles, J. Mas, D. Fernandez, J. Almazan, L.P. de las Heras , "ICDAR 2013 Robust Reading Competition", In Proc. 12th International Conference of Document Analysis and Recognition, 2013, IEEE CPS, pp. 1115-1124. [pdf] [poster] [presentation]

  2. D. Karatzas, S. Robles Mestre, J. Mas, F. Nourbakhsh, P. Pratim Roy , "ICDAR 2011 Robust Reading Competition - Challenge 1: Reading Text in Born-Digital Images (Web and Email)", In Proc. 11th International Conference of Document Analysis and Recognition, 2011, IEEE CPS, pp. 1485-1490. [pdf] [presentation]

  3. A. Shahab, F. Shafait, A. Dengel, "ICDAR 2011 Robust Reading Competition - Challenge 2: Reading Text in Scene Images",  In Proc. 11th International Conference of Document Analysis and Recognition, 2011, IEEE CPS, pp. 1491-1496. [pdf]

 

Important Dates
  • 15 December: Web site online
  • 15 January: Registration of interest
  • 28 February: Training datasets available
  • 30 March: Test datasets available
  • 8 April: Submission of results
  • 19 April: Method descriptions due