My competitions

The 1st Eye Movement Verification and Identicication Competition (EMVIC 2012)

The competition provided a common ground in a form of several datasets to benchmark the eye movement biometric methods derived by the participants. Our subsequent work with the results and the datasets allowed providing recommendations related to the eye movement data collection, measuring eye movement quality, and deciding when to record samples from the subjects to ensure meaningfulness of current and future benchmarking results.

Two types of the datasets were employed for the competition: uncalibrated and calibrated. Uncalibrated datasets were collected with a goal of minimizing data capture time, i.e., without calibration procedure or equipment adjustments. Therefore, captured data quality could not be controlled. Calibrated datasets were captured with every precaution to obtain highest possible data quality, i.e., equipment was adjusted and re-adjusted when necessary to ensure minimum calibration error and data loss.

More details about the competition is available on the EMVIC 2012 Competition website.

The 2nd Eye Movement Verification and Identicication Competition (EMVIC 2014)

Encouraged by the positive outcome from the first EMVIC we decided to organize the second edition of the competition. This time the competition was more challenging because eye movements recorded during a free observation of images (human faces) were used as an input. Therefore, the results were much worse.

More details about the competition is available on the EMVIC 2014 Competition website.

The 1st Look and Click Competition (LAC 2016)

As far as we know, the competition was the first attempt to fuse two different kinds of behavioral biometrics: mouse dynamics and eye movement biometrics. Mouse dynamics were collected without any special equipment, while an affordable The Eye Tribe eye tracker was used to gather eye movement data at a frequency of 30 Hz, which is also potentially possible using a common web camera. The aim of the competition was to provide an opportunity to compare the performance of methods for identifying people using their mouse and eye movement characteristics.

As always we published datasets of eye and mouse recordings in a simple TSV format. More datails available on the LookAndClick competition web page.

Look&Click competition was an official competition for the 9th IAPR International Conference on Biometrics