Three-dimensional face model adjusting method

Abstract

The invention discloses a three-dimensional face model adjusting method, which comprises the following steps: appointing at least 55 initial characteristic points on a three-dimensional face model and demarcating 6 characteristic areas; carrying out symmetrization adjustment locally and globally on the initial characteristic points; then globally adjusting the proportion of the symmetrically adjusted three-dimensional characteristic points; and carrying out nonlinear least squares optimization on the proportionally adjusted three-dimensional characteristic points to adjust the side face and adopting a Laplace morphing algorithm to solve the linear system of equations of the initial characteristic points and the three-dimensional characteristic points after side face adjustment so as to obtain the adjusted three-dimensional face model. The invention adopts a Laplacian morphing technology maintaining detailed characteristics so as to retain most detailed characteristic information on the face at the time of adjustment and beautifying, the algorithm is clear, the interface is friendly, and the result is robust, so the method can be used in the fields of virtual face lifting, network video chat, computer game, video conference, computer animation and the like.

Description

technical field [0001] The invention relates to the field of computer graphics and image processing, in particular to a method for adjusting a three-dimensional human face grid model. Background technique [0002] Needless to say, in daily life, people care a lot about whether a person's face is beautiful or not. For example, girls like to make themselves more beautiful through makeup, and more and more people are willing to spend money to go to beauty parlors for plastic surgery. In recent years, many researchers have done a lot of research on what kind of human face is beautiful and how to make it more beautiful. Some researchers have verified that whether a person is beautiful is closely related to the three factors of symmetry, classicism and golden ratio through previous theories and real experimental data, and proposed a set of how to calculate the two-dimensional face For the method of image beauty value, see K.Schmid, D.Mark and A.Samal. Computation of a face attra...

AI Technical Summary

Problems solved by technology

This method learns some beautiful face image databases through machine learning, and then transfers the learned features to unbeautified images, and performs nonlinear transformation on the entire image, and only slightly changes the original image. In the case of modification, a beautified face image with outstanding effects can be obtained, see T.Leyvand, D.Cohen-Or, G.Dror and D.Lischinski.Data-driven enhancement of facial attractiveness.ACM Transactions on Graphics, 2008. However, this method is only suitable for the beautification of two-dimensional face images, and it cannot directly adjust and beautify the three-dimensional face mesh model

Images