摘要
眼睛包含了多种重要的信息,眼睛定位在人脸检测及人脸识别技术中有着极其重要的实用价值。但传统的基于几何特征的眼睛定位方法在多角度视线方向上存在着不同程度的定位不够准确或计算量大的缺点,文章提出了一种多角度视线方向上的眼睛定位方法。在初步定位人脸区域后,采用主成分分析(Principal Component Analysis,PCA)方法在人脸的上半部分计算眼睛的位置。实验证明了算法的有效性。
Eyes contain a variety of important information,eye detection has important practical value in human face detection and face recognition technology.But the traditional detection methods based on geometrical characteristic are not accurate enough and large computational,this paper presented a new eye detection method.Using of PCA method in the upper half of the face to calculate the position of the eyes.Experimental results show the effectiveness of the algorithm.
作者
于琼
樊银涛
YU Qiong,FAN Yin-tao(Dept of Computer Science,Wuhan University of Technology,Wuhan 430063,China)
出处
《电脑知识与技术》
2011年第2期870-872,共3页
Computer Knowledge and Technology