Robust ReadingCompetition

Contact - ICDAR2017 Robust Reading Challenge on COCO-Text

  • Raúl Gómez,
  • Baoguang Shi,                
  • Lluís Gómez,                          
  • Lukas Neumann,                   
  • Andreas Veit,                       
  • Jiri Matas,                           
  • Serge Belongie,
  • Dimosthenis Karatzas,

Computer Vision Centre, Barcelona, Spain
Cornell University, USA
Computer Vision Centre, Barcelona, Spain
Czech Technical University, Czech Republic
Cornell University, USA
Czech Technical University, Czech Republic
Cornell University, USA
Computer Vision Centre, Barcelona, Spain


Raul Gómez is a first year PhD student advised by Dr Dimosthenis Karatzas and Dr Jaume Gibert at Centre Tecnològic de Catalunya (Eurecat) and Computer Vision Center (CVC). He received his BS degree in Telecommunications Engineering from Universitat Politècnica de Catalunya (UPC) and his MS degree in Computer vision from Universitat Autònoma de Barcelona (UAB). He is currently working in scene text recognition

Baoguang Shi is a fourth-year PhD student (advisor: Prof. Xiang Bai) of the School of Electronic Information and Communications, Huazhong University of Science and Technology (HUST), where he received his B.Eng. degree in Electronics and Information Engineering in 2012. During 2014, he worked as an intern at Microsoft Research Asia (MSRA). Currently, he is paying a one-year visit at Cornell Tech in New York, where he works with Prof. Serge Belongie.

His research focuses on reading text in natural images. In this field, he has published 7 papers on ICDAR, CVPR, Pattern Recognition, etc. He is the major contributor and maintainer of SIW-13, a first-of-its-kind dataset for script identification in the wild. He is also a maintainer of the COCO-Text dataset.  

Andreas Veit is a third year PhD student in Computer Science working with Serge Belongie at Cornell University and Cornell Tech. His research interests include Deep Learning, Computer Vision, Machine Learning and Human-in-the-Loop Computing. He is also interested in applications concerning sustainability. He is the major contributor and maintainer of the COCO-Text dataset.

He received a BS and MS degree in Information Engineering and Management from Karlsruhe Institute of Technology (KIT), Germany, where he worked with Hartmut Schmeck. He also worked as visiting scholar with Katia Sycara in the Carnegie Mellon School of Computer Science, and as research assistant in the Energy Informatics Group at Technical University of Munich.

Jiri Matas is a full professor at the Center for Machine Perception, Czech Technical University in Prague. He holds a PhD degree from the University of Surrey, UK (1995). He has published more than 200 papers in refereed journals and conferences.

His publications have approximately 6000 citations in the ISI Thomson-Reuters Science Citation Index and about 26000 in Google scholar. His h-index is 28 (Thomson-Reuters Web of Science) and 56 (Google scholar) respectively.  J. Matas has served in various roles at major international computer vision conferences (e.g. ICCV, CVPR, ICPR, NIPS, ECCV), co-chairing ECCV 2004, CVPR 2007 and ECCV 2016.

He is on the editorial board of IJCV and was the Associate Editor-in-Chief of IEEE T. PAMI. His research interests include object recognition, image retrieval, tracking, sequential pattern recognition, invariant feature detection, and Hough Transform and RANSAC-type optimization.

Serge Belongie received a B.S. (with honor) in EE from Caltech in 1995 and a Ph.D. in EECS from Berkeley in 2000. While at Berkeley, his research was supported by an NSF Graduate Research Fellowship. From 2001-2013 he was a professor in the Department of Computer Science and Engineering at University of California, San Diego.

He is currently a professor at Cornell Tech and the Department of Computer Science at Cornell University. His research interests include Computer Vision, Machine Learning, Crowdsourcing and Human-in-the-Loop Computing. He is also a co-founder of several companies including Digital Persona, Anchovi Labs and Orpix. He is a recipient of the NSF CAREER Award, the Alfred P. Sloan Research Fellowship, the MIT Technology Review “Innovators Under 35” Award and the Helmholtz Prize for fundamental contributions in Computer Vision.

Dimosthenis Karatzas is a Senior Research Fellow at the Computer Vision Centre, Universitat Autónoma de Barcelona, Spain. He received his PhD from the University of Liverpool, UK in 2003. He has co-authored over 90 publications in refereed journals and conferences.

He is leading the Robust Reading research team at the Computer Vision Centre, and has been principal investigator on numerous research and knowledge transfer projects. In 2013 he received the IAPR / ICDAR Young Investigator Award.

D. Karatzas has served in various roles at major conferences in his field (ICDAR, DAS, CBDAR, ICPR, ICFHR), including co-chairing IWRR 2016, CBDAR 2015 and IWRR 2014. D. Karatzas is a lead organiser of the Robust Reading Competitions series. He served as a guest editor for the Int. Journal of Document Analysis and Recognition special issue on “Robust Reading” in 2015.

D. Karatzas has been a founding member and a member of the executive committee of the UK Chapter of the SPIE, while he is currently the chair of IAPR TC-11 (Reading Systems), a member of the IAPR-Industrial Liaison Committee and member of the IEEE, the SPIE and the IAPR. In 2007 D. Karatzas co-founded the spin-off company TruColour, UK, which specializes on perception-based color calibration solutions.

Important Dates
  • March, 13: COCO-Text available. (train/val/test).

  • March, 19: Cropped words dataset available. (train/val).

  • March, 23: Annotations updated (v1.4).

  • March, 30: Cropped words dataset updated (v1.4).

  • May, 23:    Submissions opening.

  • June, 30: Submission of results deadline.

  • November, 10-15: Results presentation.