Classification of gaze preference decision for human-machine interaction using eye tracking device

This paper aims at classifying a gaze preference decision made taking individual difference into account. A proposed method focuses on a likelihood of a chosen face to the subject’s eye movement data measured by an eye tracking device and classifies the decision using an inferential statistical theory. A system is designed as changing displayed visual stimuli flexibly using the measured eye movement data as an image switcher. In order to discuss the proposed method, experiments using the image switcher are done. Two conditions are compared in experiments, i.e., one is when two faces are displayed side by side statically, and the other is when the face the subject tries to look at disappears dynamically. Thus, the proposed classification method is enhanced by discussing interesting results of the visual-psychophysical experiments, to supplement and progress the gaze cascade effect, which is a well known hypothesis of a psychophysical experiment.