Iteration interpolation method based on face triangle mesh adaptive subdivision and Gauss wavelet

Abstract

The invention discloses an iteration interpolation method based on face triangle mesh adaptive subdivision and Gauss wavelet. First, performing triangulation to a face model through a mesh optimized face subdivision method to obtain an optimal triangle; determining whether a spatial triangle is intersected or not, calculating depth information of an interpolation point through a two-dimension Gauss wavelet function on the basis of status of three vertexes of the spatial triangle to obtain a complete three-dimension coordinate of the interpolation point; obtaining the two-dimension coordinate (x, y) of the interpolation point, after finishing determining the two-dimension coordinate (x, y) of the interpolation point, performing recovery to a z axis of the interpolation point through the two-dimension Gauss wavelet function; determining the value of the interpolation point at the z axis and determining the optimal value of m according to the three vertexes of x, y, and z. The beneficial effects of the invention are: failure in shaping a recognizable three-dimension face model due to insufficient three-dimension characteristic points is effectively avoided, and modeling effect is impressive.

Description

technical field [0001] The invention belongs to the technical field of face recognition, and relates to an iterative interpolation method based on face triangular mesh self-adaptive subdivision and Gaussian wavelet. Background technique [0002] The bottleneck of 3D dynamic face recognition is that in the process of estimating and modeling 3D face deformation through 2D face pictures, because there are too few data points, it is almost impossible to obtain a face model with many 3D data points. Accuracy is low. However, with the gradual development of optical three-dimensional shape measurement technology, many effective three-dimensional face shape measurement technologies have emerged, which improves the possibility of dynamic recognition of three-dimensional faces. However, because directly emitting structured light to the face is not friendly to the person being identified, and at the same time cannot achieve covert identification, which greatly reduces its application ...

AI Technical Summary

Problems solved by technology

[0002] The bottleneck of 3D dynamic face recognition is that in the process of 3D face deformation estimation and modeling through 2D face pictures, it is almost impossible to obtain a face model with many 3D data points because of too few data points, resulting in low accuracy

[0014] When collecting 3D face features, due to too few data points in the data point cloud structure of 3D face recovery through 2D pictures, it is impossible to effectively realize 3D face recognition. The iterative interpolation method adapted to subdivision and Gaussian wavelet shapes a 3D face model that can be used for recognition

Images