基于边缘统计和特征定位的人脸姿态估计方法  

Face Pose Estimation Based on Edge Statistics and Feature Location

作　　者：王燕群[1] 童卫青[1] 张昌明[1] 

机构地区：[1]华东师范大学计算机科学与技术系,上海200241

出　　处：《计算机系统应用》2011年第4期86-90,共5页Computer Systems & Applications

摘　　要：提出基于整体信息和基于局部信息的人脸姿态估计方法,并对两种方法进行比较分析。基于边缘统计特征的人脸姿态估计算法先利用人脸整体信息,提取边缘统计特征,再使用线性回归算法建立特征与姿态间的对应关系。基于特征定位的人脸姿态估计是一种基于局部信息的算法,该算法先使用数理形态学运算精确定位鼻孔,再根据鼻孔与眼睛的位置关系进行人脸姿态估计。实验结果表明,本文的算法具有准确度高,计算速度快的优点。This paper proposes an edge statistical-based face pose estimation method,which uses the overall information to extract the features firstly.And then the linear regression algorithm is applied to build the corresponding relationship between features and poses.Feature location-based face pose estimation is another method proposed in this paper.It is a local information-based method,which utilizes mathematical morphology operators to pinpoint the nostril.Then according to the location of the nose and eyes,face poses are estimated.The aforementioned methods are compared in the same dataset.Experimental results show that the method can accurately and fast estimate face pose.

关 键 词：人脸姿态估计 边缘统计特征 鼻孔定位 数理形态学 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]