基于肤色与人脸运动相结合的自动表情识别算法研究

Research on automatic facial expression recognition algorithm based on skin color and face movement

基于肤色与人脸运动相结合的自动表情,对其识别算法进行研究。通过RGB将图像转为YIQ颜色空间,在YIQ中第I维中进行图像数据的提取,在二值图像中将背景和肤色分割出来。采用Pareto优化算法进行人脸表情特征的选取,算法计算量少,构结简单,运行速度快,能对小角度人脸肤色、人脸面部表情变化、人脸旋转、人脸面部存在遮挡物等情况准确检测和跟踪。实验表明,对于人脸小角度转动,该算法能较好适应;对于人眼的状态,该算法不受影响;对于丰富的面部表情变化和不同的肤色均能更好地适应,具有一定的稳定性。

In this paper, the automatic facial expression based on the combination of skin color and face motion is studied. The image is transformed into YIQ color space by RGB, and the image data is extracted in the I dimension of YIQ, and the back-ground and skin color are segmented in the two valued image. By using Pareto optimization algorithm to select facial expression fea-ture, this algorithm has less calculation, simple structure, fast running speed, accurate detection and can track the obstructions of small angle face skin color, facial expression, face rotation and face. Experiments show that the algorithm can adapt to small angle rotation of human face. For human eyes, the algorithm is not affected, can better adapt to the rich facial expression changes and different skin colors, and has a certain stability.