Full-automatic three-dimensional human face detection and posture correction method

Abstract

The invention belongs to the fields of computer vision and computer graphics, relating to a full-automatic robust three-dimensional human face detection and posture correction method. The method comprises the following steps of: by using three-dimensional curved surfaces of human faces with complex interference, various expressions and different postures as input and carrying out multi-dimensional moment analysis on three-dimensional curved surfaces of human faces, roughly detecting the curved surfaces of the human faces by using face regional characteristics and accurately positioning the positions of the nose tips by using nose tip regional characteristics; further accurately segmenting to form completed curved surfaces of the human faces; detecting the positions of the nose roots by using nose root regional characteristics according to distance information of the curved surfaces of the human faces; establishing a human face coordinate system; automatically correcting the postures of the human faces according to the human face coordinate system; and outputting the trimmed, complete and posture-corrected three-dimensional human faces. The method can be used for a large-scale three-dimensional human face base. The result shows that the method has the advantages of high speed, high accuracy and high reliability.

Description

technical field [0001] The invention belongs to the fields of computer vision and computer graphics, and in particular relates to a fully automatic and robust three-dimensional human face detection and attitude correction method. Background technique [0002] In recent years, with the advancement of 3D reconstruction software and hardware technology, 3D face has been widely used in many fields, such as identity authentication, facial behavior analysis, and computer animation design. Detection and pose correction of 3D faces is the first and crucial step in the above applications. Manually performing these operations will be very time-consuming and laborious, and in applications such as identity authentication, automatic detection and posture correction are also necessary. But similar complex backgrounds (such as clothes, hair, etc.), expressions, etc. make this job very challenging. [0003] The background technologies described in [1] and [2] all use the curvature informa...

AI Technical Summary

Problems solved by technology

Manually performing these operations will be very time-consuming and laborious, and in applications such as identity authentication, automatic detection and posture correction are also necessary

But similar complex backgrounds (such as clothes, hair, etc.), expressions, etc. make this job very challenging

[0003] The background technologies described in literature [1] and [2] all use the curvature information of the surface to perform 3D face detection or feature location, but features such as curvature will be very unstable under the interference of noise

The background technology described in literature [3] uses the method of finding face symmetry planes to solve the problems of 3D face detection and pose correction, but the face symmetry planes are prone to errors in the presence of expressions

The background technology described in literature [4], [5] utilizes the algorithms of multi-stage filters combined with classifiers, but the disadvantage of these algorithms is that the results are largely dependent on the performance of the classifier

There are unavoidable problems in the above background technologies, which inevitably restrict the development of 3D face detection and posture correction technology

Images