Electrooculography dataset for reading detection in the wild
Shoya Ishimaru, Takanori Maruichi, Manuel Landsmann, Koichi Kise, Andreas R. Dengel · 2019
Because of the diversity of document layouts and reading styles, detecting reading activities in real life is a challenging task compared to the detection in the laboratory setting. For contributing to the implementation of robust reading detection algorithms, we introduce a dataset which contains 220 hours of sensor signals from JINS MEME electrooculography glasses and corresponding ground truth activity labels. As a baseline study, we propose a statistical feature based reading detection approach and evaluate it on the dataset.