Large-scale face deformation method

The invention discloses a large-scale face deformation method. The method comprises the following steps: obtaining a plurality of face feature points according to a face feature point recognition algorithm; calculating forehead feature points according to the eyebrow feature points, calculating cheek feature points according to the contours of the nose and the face, and increasing a deformable area of the face; selecting n control vertexes from all the feature points, wherein 3 < = n < = the number of the feature points; according to the deformation constraint conditions and the control vertexes, calculating all deformed face feature points through a moving least square method (MLS), so as to enable the deformed face to be more natural; performing interpolation processing on the feature points before and after deformation by utilizing B-spline interpolation to improve the density of the feature points and improve the smoothness of the edge of the human face after large-scale deformation; carrying out triangul