A method and system are provided. The method includes positioning facial feature base points in a face image in an obtained image. A deformation template is obtained, the deformation template carrying configuration reference points and configuration base points. In the facial feature base points, a current reference point is determined corresponding to the configuration reference point, and a to-be-matched base point is determined corresponding to the configuration base point. A target base point is determined that corresponds to the configuration base point and that is in a to-be-processed image. The target base point and the corresponding to-be-matched base point forming form a mapping point pair. A to-be-processed image point is mapped to a corresponding target location according to a location relationship between the target base point and the to-be-matched base point, and a location relationship between the mapping point pair and the to-be-processed image point.