讨论人机交互中的眼姿势辨别技术

Discussion on Technologies of Eye Gesture Detection in Human-computer Interaction

目的:讨论人机交互中各种眼姿势(眼睛运动模式)的辨别技术。眼姿势的准确辨识是成功实现新型的眼机接口的关键环节之一。方法:根据眼电信号产生的生理机制和采集方法,分析各种眼姿势的特点,包括基本眼动模式(眼睛上移、下移、左移、右移)、眨眼模式、凝视模式等,并据此研究对应的辨识技术。结果:应用阈值估计算法、积分算法、模板匹配算法等可将基本眼动模式、眨眼模式、凝视模式初步辨识出来。结论:对各种眼姿势进行特征分类、准确辨识,为设计眼机接口、实现人机交互提供了基础。

Objective To discuss all kinds of technologies of detecting eye gestures in human-computer interaction.It is one of the key points for precise identification of eye gestures to successfully design a novel eye-computer interface.Methods The principle of generating electrooculogram（EOG） signals and the method of sampling EOG signals were introduced firstly.Then,features of eye gestures including the basic eye motions（up shift,down shift,left shift,and right shift）,blinking and gaze were elaborated.Based on these materials,their corresponding detecting methods were discussed in detail.Results Different eye gestures could be detected by adopting threshold estimation algorithm,integration algorithm or module matching algorithm.Conclusion Through characterizing all kinds of eye gestures and their identification technologies,it provides a helpful reference to research and design the eye-computer interaction interface.