3D Face Pose Estimation Based on Face Feature Points and Linear Regression

Qiu Li-mei · Journal of Sanming University · 2008

In this paper,the improved method of active shape model is used to extract face feature points accurately,then a coarse estimation value is obtained by using face feature points,and takes this coarse value as the starting value,precise value of 3D face pose is obtained based on linear regression iteration.The experiment results show that the new method not only can achieve steady and only 3D face pose,but also has better estimation accuracy compared with the same kind of method.

Read the paper · More papers on PaperTik