RCTW-17

ICDAR2017 Competition on Reading Chinese Text in the Wild

Introduction

RCTW-17 is a competition on reading Chinese Text in images. For training and testing, we provide a large-scale dataset that consists of various kinds of images, including street views, posters, menus, indoor scenes, and screenshots. See Dataset and Tasks for details.

News

  • The rctw-17 train dataset has been refineed to provide better and clearer annotations.We advise that all competitors should redownload the new rctw-17 train dataset from the dataset page!

  • The rctw-17 test dataset has been uploaded to test your model.All competitors can download the rctw-17 test dataset from the dataset page for testing!

Example Images

Example images

Organization Team

  • Baoguang Shi PhD student of the School of Electronic Information and Communications, Huazhong University of Science and Technology, China
  • Cong Yao Senior researcher at Megvii Technology Inc., China
  • Serge Belongie Professor at Cornell Tech and the Department of Computer Science at Cornell University, United States
  • Shijian Lu Head of Visual Attention Lab, Institute for Infocomm Research, A*STAR
  • Xiang Bai Professor of the School of Electronic Information and Communications, Huazhong University of Science and Technology

Important Dates

  • January 20 - April 30, 2017: Registration open
  • April 15, 2017: Test dataset available
  • April 15, 2017: Submission open
  • April 30, 2017: Submission deadline