OMEG: Oulu Multi-Pose Eye Gaze Dataset

Data is in a very important position for pattern recognition tasks including eye gaze estimation. In the literature, most researchers used normal face datasets, which are not specifically designed for eye gaze estimation. As a result, it is difficult to obtain fine labeled eye gaze direction. Therefore large datasets with well-defined gaze directions are desired. To facilitate related researches, we collect and establish the Oulu Multi-pose Eye Gaze Dataset. Inspired by the psychological observation that gaze direction is intrinsically linked with the head orientation, we are devoted to a new data set of eye gaze images captured under multiple head poses. It finally results in a dataset containing over 40K images from 50 subjects, who are asked to fixate on 10 special points on screen under different poses respectively. We investigate a new eye gaze estimation approach by using the IGO based facial description, and compare it with other popular eye gaze estimation approaches to provide the baseline results on our dataset.