IWRR aims at bringing together computer vision researchers and practitioners with an interest in reading systems that operate on images acquired in unconstrained conditions, such as scene images and video sequences, born-digital images, wearable camera and lifelog feeds, social media images, etc. The particular focus of the workshop is on the automatic extraction and interpretation of textual content in images, and applications that use textual information obtained automatically by such methods.

This topic is gaining momentum in the computer vision community as new datasets are being released and the application areas are being diversified. The workshop aims to offer a forum for researchers to share experiences and latest results in the area, and to discuss current trends and the evolution of the Robust Reading Competition (RRC) which has attracted to date over 1,500 researchers and more than four thousand submissions. Reporting recent results on standard datasets such as the ICDAR RRC 2015 dataset on incidental scene text or the Coco-Text dataset is particularly encouraged.

The 2nd International Workshop on Robust Reading (IWRR 2016) is the succession of the 1st IWRR workshop that was held in Singapore as a satellite workshop of ACCV 2014.

Call for papers

The topics of interest include among others:

  • Scene text localisation, segmentation, and recognition
  • Reading scene and/or overlaid text in video sequences
  • Word spotting
  • End-to-end reading systems
  • Text localisation and recognition in born-digital images
  • Restoration of camera captured paper documents
  • Quality estimation and degradation modelling of camera-captured text
  • Performance evaluation and metrics
  • Robust reading applications
  • Graphical content interpretation in complex settings

See the full call for papers here.

Contact Information

For any inquiries you may have regarding the conference, please contact the organisers at: iwrr2016@cvc.uab.es