Three-dimensional face recognition device and method based on three-dimensional point cloud

Abstract

The invention discloses a three-dimensional face recognition device and method based on three-dimensional point cloud; the device comprises a characteristic area detection unit for positioning a three-dimensional point cloud characteristic area; a mapping unit for normalized mapping the three-dimensional point cloud to a depth image space; a data calculating unit using Gabor filters in different dimensions and directions to calculate responses in different dimensions and directions of three-dimensional face data; a storage unit for training a visual dictionary of the obtained three-dimensional face data; a mapping calculating unit for implementing histogram projection to the visual dictionary with respect to the Gabor response vector obtained by each pixel; a classification calculating unit for coarse classification of the three-dimensional face data; and an identification calculating unit for identifying the three-dimensional face data. By employing the disclosed technical scheme, the detail texture description ability of the three-dimensional data is stronger, and the adaptability to the quality of the input three-dimensional point cloud face data is better, thus the application foreground is better.

Description

technical field [0001] The present invention relates to the technical field of three-dimensional face recognition, in particular to a three-dimensional face recognition device and method based on three-dimensional point clouds. Background technique [0002] Compared with 2D face recognition, 3D face recognition has the advantages of being robust to illumination and less affected by factors such as posture and expression. Therefore, after the rapid development of 3D data acquisition technology and the great improvement in the quality and accuracy of 3D data, Many scholars devote their research to this field. [0003] CN201010256907 proposes the relevant features of three-dimensional bending invariant to describe the characteristics of human face. This method extracts the relevant features of the bending invariant by encoding the local features of the bending invariant of adjacent nodes on the surface of the three-dimensional face; signs the relevant features of the bending i...

AI Technical Summary

Problems solved by technology

Most of the initial work in this field is to use the information of 3D data: such as curvature, depth, etc. to describe the face, but because there are a lot of data noise in the collection of 3D data, features such as curvature are sensitive to noise. characteristics, making it a feature description vector of a 3D face with low recognition accuracy; later, after mapping the 3D data to the depth map data, many 2D face appearance features began to be applied to this field, such as principal component analysis. (PCA) and Gabor filter features; but these features also have their own shortcomings: (1) For PCA features, because they belong to the global representational features, the ability to describe the detailed texture of three-dimensional data is insufficient (2) For Gabor filters feature, due to the noise problem of 3D data, its ability to describe 3D face data depends on the quality of the acquired 3D face data

Images