基于椭圆模型和神经网络的人脸姿态估计方法  

Face Pose Estimation Based on Elliptical Model and Neural Network

作　　者：刘淼[1] 郭东伟[1] 马捷[1] 孙浩翔[1] 周春光[1] 

机构地区：[1]吉林大学计算机科学与技术学院,长春130012

出　　处：《吉林大学学报（理学版）》2008年第4期687-690,共4页Journal of Jilin University:Science Edition

基　　金：吉林省科技发展计划项目基金(批准号:20060116)

摘　　要：基于椭圆模型和神经网络方法,提出一种人脸姿态估计方法.先采用椭圆模型对人脸边界进行拟合,确定眼睛和嘴在椭圆中的位置,再应用BP神经网络对位置参数和人脸姿态参数的关系进行学习,从而对人脸姿态进行估计.实验结果表明,用该方法对较大范围内的人脸转动进行估计,结果比较准确.The present paper presents a new method based on the elliptical model and artificial neural network for estimating the pose of human face. First, elliptical model is used to fit the boundary of face and the positions of eyes and mouth are located. Second, the BP neural network is trained to learn the relationship between position parameters of eyes and mouth and the parameters of pose. The experimental results demonstrate that this method can estimate accurately pose of faces rotating in a large scope.

关 键 词：人脸姿态估计 椭圆模型 人工神经网络 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]