Tensity Research Based on the Information of Eye Movement

TL;DR

This paper proposes a method to measure tension based on eye movement features, including pupil and gaze parameters, to assess mental state during human-robot interaction.

Contribution

It introduces a novel approach to tension measurement using eye movement indices and parameter extraction under normal lighting conditions.

Findings

The method effectively identifies tension from eye images.

Eye movement parameters correlate with mental tension levels.

Experimental results validate the approach's accuracy.

Abstract

User's mental state is concerned gradually, during the interaction course of human robot. As the measurement and identification method of psychological state, tension, has certain practical significance role. At presents there is no suitable method of measuring the tension. Firstly, sum up some availability of eye movement index. And then parameters extraction on eye movement characteristics of normal illumination is studied, including the location of the face, eyes location, access to the pupil diameter, the eye pupil center characteristic parameters. And with the judgment of the tension in eye images, extract exact information of gaze direction. Finally, through the experiment to prove the proposed method is effective.