Facial point detection based on ASMS learning from 3D models

Detecting a set of facial points is a crucial phase for facial expression analysis and face recognition, yet the robust facial point detector is yet to be developed. In this paper we present a method based on Active Shape Model of Subsets (ASMS) learning from 3D models to drastically reduce the time needed to search for a point's location and increase the accuracy and robustness of the algorithm. Using 3D Information allows us to expand training samples and set up complete point distribution models (PDMs). On the other hand, training samples are grouped into different subsets, which makes detection of the points very fast and the algorithm robust to pose and illumination variations as well. In order to improve the accuracy of location, objective function and parameter optimization process of Active Appearance Model (AAM) will be introduced in ASMS. The proposed point detection algorithm was tested on WHU-3D-2D database, the results of which showed we outperform current state of the art point detectors.