ARM平台下人眼定位研究与系统实现

Study and Implementation of Eye Locating System Based on ARM Embedded System

实现了基于嵌入式ARM实验平台的人眼定位系统,提出利用背景差分法和大津方法确定人脸区域的方法。结合RGB空间下的眉毛和眼球的灰度分布特点,使用灰度投影法提取眉眼区域,然后根据眼球的特征精确定位眼球的位置,实验结果表明该系统能够准确实时的完成人眼的定位。

A quick and accurate eye locating system is designed in this paper and an algorithm by applying background difference and Otsu method for segmenting the face region is proposed.It is combined with the gray distribution feature of eyebrow and eyeball based on RGB color space to extract the region which includes eyebrow and eye by gray projection algorithm（GPM）.At last locate the eyeball by its feature accurately.The results of experiment suggest that the system could locate the position of eyes in the face region accurately in given time.