Face segmentation method and device

The invention discloses a face segmentation method and device, and belongs to the technical field of image processing. The face segmentation method comprises the following steps: constructing a deformable face model according to pre-collected three-dimensional face point cloud data; wherein a face part represented by each data coordinate point in the deformable face model is marked; adjusting deformation parameters of the deformable face model to obtain a plurality of different three-dimensional face models; projecting the three-dimensional face models into two-dimensional face images respectively; and according to the projection relationship between the three-dimensional face model and the two-dimensional face image and the face part represented by each data coordinate point in the deformable face model, carrying out segmentation processing on the two-dimensional face image. 本申请公开了一种人脸分割方法及其装置，属于图像处理技术领域。该人脸分割方法包括：根据预先采集的三维人脸点云数据，构建可形变人脸模型；其中，所述可形变人脸模型中每个数据坐标点表示的人脸部位已标记；调整所述可形变人脸模型的形变参数，得到多个不同的三维人脸模型；将所述三维人脸