Image Synthesis of Eye Areas for Perceptually Establishing Eye-contacts between Video Conference Participants

Recently, the spread of Web cameras has facilitated video-conferencing as a means of communication. Since a Web camera is usually located outside the display while the user looks at his/her partner in the display, there is a problem that they cannot establish eye contact with each other. Various methods have been proposed to solve this problem, but most of them required specific sensors, and robust and accurate feature extraction for various appearances to densely associate facial feature points of the images. In this paper, we propose a method that transforms the eye areas to synthesize eye contact using a single camera that is commonly implemented in laptop computers. Concretely, we implemented a system which transforms the user's eye areas in an image to his/her eye image with a straight gaze to the camera only when the user's gaze falls in a range that the partner would perceive eye contact. We then confirmed the effectiveness of the proposed method in terms of accuracy of the gaze area classification, subjective evaluation score for eye contact, and accuracy of eye contact through experiments.