Finally, the precise contour of the object is extracted by the fusion of motion template and color clustering result.

最后，将运动目标的初始模板和彩色精确分割结合起来提取出具有精确边缘的运动目标。

youdao

Facial features extraction algorithms presented are based on deformable template model. In this paper, facial features are described accurately about contour but not express simply with data.

根据动态模板匹配理论，提出了提取人脸面部特征的系列算法，特征是精确的轮廓描述而非简单的数字表达。

youdao

According to matching the head template with the contour image of follow-up frames, it can implement the head detection and tracking with image sequence.

对后续帧，通过与前一帧进行头部模板匹配，完成目标图像序列的头部检测跟踪。

youdao