The competition is open to academic, research and industrial institutions. Each user will receive information about the competition rules and, after a registration procedure, a login/password to access the restricted part of the contest web site, in order to download the training set and manage his/her personal information and uploaded files.
The results of all the participants will be included in the final contest report, in anonymous form if requested. With regard to this aspect, it is worth to point out that results published in the contest report cannot be used for advertising or other commercial purposes. The goal of the competition is merely to assess the state-of-the-art.
The dataset contains more than 10.000 images of cells and has been acquired and verified by experts of the SNP. Dataset is split in a training set given to participants and a test set retained by the contest organizers for benchmarking. Splitting is done at the image level, meaning that the cells belonging to the same image are in the same set. To every cell of each set it is randomly attributed an ID.
Participants will also receive some scripts for checking and tuning their algorithm. These programs will also be used by the contest organizers for performance evaluation of the submitted methods on the private test set.