基于深度数据的空间人脸旋转角度估计

提出一种基于三维人脸深度数据的人脸姿态计算方法。利用人脸的深度数据以及与其一一对应的灰度图像，根据微分几何原理和相应的曲率算法与人脸数据中的灰度特征对人脸面部关键特征点定位，进而计算出人脸姿态在三维空间中的3 个姿态角。实验证明该方法能在姿态变化情况下实现对人脸旋转角的准确估计，为进一步的人脸识别和表情分析提供基础。

Estimation of face rotation based on depth data

A novel method of calculating the rotation of face is proposed based on the 3Dfacial depth information. Facial feature points are extracted by the depth map and itscorresponding gray image according to differential geometry theory, curvature algorithm andintensity features generated by face data. And then the three pose angles of the face in the spacewill be calculated. Experimental results show that the proposed algorithm can achieve an accurateestimation of face rotation with the variation of pose and provide a priori knowledge for facerecognition and facial expression analysis.