News
April 15, 2024: Test B is now live! Teams with valid scores from Test A have advanced to this stage. A download link for Test set B has been dispatched via email. Note that only one submission per day is permitted during the Test B phase to discourage excessive parameter tuning. Best results should be displayed on the leaderboard prior to the conclusion of Test B, as final rankings will be influenced by these scores.
March 13, 2024: In line with an announcement from ICDAR, the competition schedule has been adjusted to allow contestants more time to optimize their algorithms. The deadline for Test A has been postponed from March 20 to April 15, and the deadline for Test B has been moved from March 31 to April 25. Please refer to the Planned Schedule for more details.
January 27, 2024: The test set A is ready, and the download link has been sent to participants via email. The submission portal and leaderboard for test set A are now accessible. When signing up for codalab, please use the same email address and team name as the ones associated with this site.
January 25, 2024: The baseline system, Graph Matching Tool, and Graph Parsing Tool have been released.
January 15, 2024: The training set is ready, and the download link will be sent to participants via email after they register.
January 10, 2024: This competition is open for registration.
Introduction
The purpose of this competition is to attract the attention of researchers in the field of Optical Character Recognition (OCR) to the challenge of recognizing handwritten chemical structures. This challenge is distinct from the traditional recognition of handwritten text and mathematical formulas, as the data format of chemical structures is more complex. Solving this problem would not only be an academic breakthrough but also have practical applications, particularly in the education of middle and high school organic chemistry. We have established a new benchmark for this issue and released a self-built dataset for handwritten chemical structure recognition, named EDU-CHEMC. We collected 60,974 images containing chemical structures from real educational settings in middle and high schools. The provided annotations include original Chemfig strings and structured strings after regularization, facilitating researchers in establishing baselines. The sole task of this competition is to accurately extract the information of the structural formulas in the images, including atoms, chemical bonds, and their connections. We hope that by hosting this competition, we can promote the development of the subfield of handwritten chemical image structure recognition.
Planned Schedule (AOE Time)
- Registration open: January 10, 2024
- Training set release: January 15, 2024
- Test set A and Leaderboard A release: January 27, 2024
- Deadline for Test set A, Test set B release: April 15, 2024
- Deadline for Test set B: April 25, 2024
- Deadline for the submitting source code and models: April 30, 2024
- Deadline for the submitting technical reports: May 10, 2024
Organizers
Contact Us
For additional information, please email us at crocs.ifly.ustc@outlook.com