IMAGE PROCESSING METHOD AND DEVICE

摘要

Provided are an image processing method and device, the method comprising: acquiring a two-dimensional target facial image; receiving an identification curve marked by a user in the target facial image, the identification curve being used to indicate the contour of a face in the target facial image; based on the identification curve, positioning the facial contour curve of the face in the target facial image by utilizing an image segmentation technology; determining the three-dimensional attitude and feature point positions of the face in the target facial image; and according to the facial contour curve, three-dimensional posture and feature point positions of the face in the target facial image, constructing a three-dimensional shape of the face in the target facial image by utilizing a preset empirical model of the three-dimensional shape of the face and a target function matching the empirical model of the three-dimensional shape of the face. The method and device reduce the complexity in constructing a three-dimensional shape of the face.