News - ICDAR2017 Competition on Multi-lingual scene text detection and script identification

03/24/2015

Updated Challenge 1 and 2 per-image vocabularies

It came to our attention that a few words that were correctly present in the localisation ground truth of the images, were not reflected in the per-image vocabularies of Challenge 1 and Challenge 2. This affects Task 4 of said tasks. The per image vocabularies have been updated to correct this error. Please download the up to date files from the respective download pages or the links below.

Challenge 1

Per image vocabularies - Training Set

Per image vocabularies - Test Set

Challenge 2

Per image vocabularies - Training Set

Per image vocabularies - Test Set

Important Dates

1 Feb to 31 Mar

  • Manifestation of interest by participants opens
  • Asking/Answering questions about the details of the competition Initial website available

1 Mar

  • Competition formal announcement

31 Mar

  • Website fully ready
  • Registration of participants continues
  • Evaluation protocol, file formats etc. available

1 Apr to 31 May

  • Train set available - training period - MLT challenge in progress -Participants evaluate their methods on the training/validation sets - Prepare for submission
  • Registration is still open

1 Jun

  • Registration closes for this MLT challenge for ICDAR-2017

1 Jun to 1 Jul

  • Test set available

1 Jul

  • Deadline for submission of results by participants

1 Nov

  • The public release of the full dataset