Three-dimensional face image recognition method based on the moment Fourier descriptor

Abstract

The invention discloses a three-dimensional face image recognition method based on the moment Fourier descriptor, and relates to the technical field of three-dimensional imaging technology. For a three-dimensional face depth map under different postures, a differential geometric correlation theory is used for correcting to the median plane, and the contour line features of a human face are extracted to turn the three-dimensional face into a two-dimensional curve which is easy to process. A novel method for combining a torque and fourier descriptor is provided for better describing the two-dimensional curve. The extracted curve features are used for carrying out face recognition. The problem of low accuracy and slow recognition speed of a conventional three-dimensional face recognition method can be solved, the calculation time can be effectively shortened, and the recognition rate is high.

Description

technical field [0001] The invention relates to the technical field of three-dimensional imaging, in particular to a method for recognizing a three-dimensional image based on a moment Fourier descriptor. Background technique: [0002] Face recognition, like palmprint recognition, fingerprint recognition, voice recognition, etc., is a biometric-based identity authentication technology. It performs identity authentication by extracting and analyzing face visual feature information, and has the characteristics of non-contact and non-invasion of privacy. , is one of the most active and potential research directions in the field of pattern recognition and machine vision, and has broad application prospects, such as in e-commerce, access control systems, etc. [0003] The initial face recognition is mainly based on two-dimensional face features, and it can achieve better recognition results under suitable conditions. However, in practical applications, the two-dimensional face re...

AI Technical Summary

Problems solved by technology

This algorithm transforms the three-dimensional data used in face recognition into two-dimensional data (isodepth lines) for processing, and reduces the complexity of data processing on the basis of retaining the original face information; at the same time, it uses an improved manifold learning method to achieve Feature extraction, recognition rate and recognition speed have been greatly improved, but this algorithm uses the frequency domain method, which has a large amount of calculation and takes a long time

[0006] For example, the application number is CN201520790722.1, which discloses a face recognition device based on three-dimensional point cloud, including a central control module, a working power supply module connected to the central control module, a wireless communication module, a face recognition module and a three-dimensional face visual dictionary library, the 3D face visual dictionary library is connected to the face recognition module, and the face recognition device based on the 3D point cloud utilizes the feature that the curvature of the nose tip area is relatively large and the point cloud distribution is relatively dense through the 3D data feature area positioning module to perform Robust precise positioning of the 3D nose tip area; and then through the Gabor filter response module, data response information at multiple scales and directions can be extracted, so as to perform in-depth local signal comparison of face images and obtain finer textures Internal characteristics, thereby improving the accuracy of the device; not only that, the device classifies the data through the SVM classifier, which improves the accuracy and reliability of the classification, thereby improving the reliability of the device, but this device does not mention How to achieve an effective method of rapid identification

Images