Evaluation of gaze-added target selection methods suitable for general GUIs

This paper examines three gaze-added methods, the Auto, Manual, and SemiAuto, that have a potential to increase the efficiency of target selection operations in general GUI environments such as MS-Windows and Mac-OS. These three methods employ the human's eye gaze and a hand (mouse operation) together to enable users to select a target even if the jittery motions of an eye and the measurement error of an eye-tracking device have occurred. The result of the experiment under an environment in which small targets are placed in a narrow layout showed that the operational efficiency with the SemiAuto method was the best among three methods; and, the SemiAuto method was the same or faster than the mouse-only operation without increasing errors greatly. Especially concerning the discontinuous selection situation (a target selection whose cursor position is randomly located), the operation with the SemiAuto method was about 31% faster than the mouse-only operation.