3D face recognition method

The invention discloses a 3D face recognition method, and relates to the technical field of face recognition, and the method comprises the steps: obtaining and preprocessing a multi-pose face image, training a multi-pose face 3D rendering model, carrying out the meshing division of a 3D face region, carrying out the shape and texture feature extraction of a finally obtained 3D face, and carrying out the matching with a face in a face sample space, thereby achieving the recognition of the 3D face. The human face recognition is completed, the natural activity process of the recognized person is not affected in the human face recognition process, the distance between the human face and the camera does not need to be restrained, and the method is applied to places with universal monitoring cameras, such as electric power business halls and used for identity recognition of people in the places. 本发明公开了一种3D人脸识别方法，涉及人脸识别技术领域，通过获取多姿态人脸图像及预处理，多姿态人脸3D渲染模型训练，将3D人脸区域做网格化划分，将最终获得的3D人脸进行形状和纹理特征提取并与人脸样本空间中人脸进行匹配，完成人脸识别，在人脸识别