基于Adaboost算法和人脸特征三角形的姿态参数估计

Pose Parameters Estimate Based on Adaboost Algorithm and Facial Feature Triangle

提出了一种基于Adaboost算法和人脸特征三角形的姿态参数估计方法。首先利用Adaboost算法训练人脸器官检测器,然后根据人脸器官的几何特征定位人脸特征点,利用获得的人脸特征点构建人脸特征三角形。当人脸发生姿态变化时,利用特征三角形的位置变化进行姿态参数的初步估计。

Pose is one of the most important elements that affect the facial image.Pose is also an important parameter in the algorithm of face analysis.The pose parameters estimate algorithm based on Adaboost and face feature triangle is introduced in the thesis.Firstly,we use adaboost algorithm to train facial feature detector,then get feature points according to facial geometric structure.After that,we can use feature points to construct facial feature triangle.When facial pose varies,the parameters could be estimated according to the position of facial feature triangle.