Techniques for estimating gaze without restricting user movements are highly desired for their potential applications. Although commercial gaze estimation systems achieve high accuracy using infrared light, gaze estimation systems with webcams have become indispensable because of their low price. The problem using webcams is that their resolution is too low to estimate the direction of eye-gaze...

This preregistered experiment examines the impact of three nonverbal cues displayed through video conference screenshots (i.e., gaze direction, distance between face and camera, camera angle) on impression formation. Actors in each portrayed one 18 cue configurations that manipulated (at on-screen, or off-screen), (close far), angle (high, eye-level, low). Study participants (N = 3,982) rated a...

Existing eye gaze tracking systems typically require an explicit personal calibration process in order to estimate certain person-specific eye parameters. For natural human computer interaction, such a personal calibration is often cumbersome and unnatural. In this paper, we propose a new probabilistic eye gaze tracking system without explicit personal calibration. Unlike the traditional eye ga...

This study investigated event-related potentials (ERP) during an oddball task in which detection of specific eye direction was required of children with and without autism. The detection of a change in eye direction elicited occipito-temporal negativity, which had two major differences between children with and without autism. First, while this occipito-temporal negativity predominated in the r...

The paper studies about a line-laser based vision system to measure structural adhesive as a non-invasive inspection. It proposes a novel vision system to measure height and width of adhesive (or object) by optical triangulation using line-laser, and analyzes for resolution, gaze angle, focal length and baseline of vision camera, proper to measurement. The validity of the proposed method was ve...

In this paper we present a non-intrusive model-based gaze tracking system. The system estimates the 3-0 pose of a user’s head by tracking as few as six facial feature points. The system locates a human face using a statistical color model without any mark on the face and then finds and tracks the facial features, such as eyes, nostrils and lip corners. A full perspective model is employed to m ...