提出一种人脸特征点跟踪方法。首先, 运用ASM 获取人脸的特征点, 然后在选用Lucas􀀁 Kanade光流算法的基础

上, 将初始帧和当前帧的前一帧有机结合起来, 共同作为当前帧的参考来进行特征点跟踪。实验结果表明该方法对特征

点的跟踪有很好的效果。-Proposed a facial feature point tracking method. First, the use of the ASM obtaining human face feature point, and then in the selection of the the Lucas 􀀁　Kanade optical flow algorithm, based on, the initial frame and the current frame before a combine, as the current frame of reference common feature point tracking . Experimental results show that the method has a good effect on the tracking of the feature point.