Unlock instant, AI-driven research and patent intelligence for your innovation.

Face authentication model generation method, authentication method, equipment and storage medium

An authentication method and authentication algorithm technology, applied in the field of face authentication, to achieve the effect of reducing costs

Active Publication Date: 2022-04-15
SHANGHAI CLEARTV CORP LTD
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The technical problem to be solved by the present invention is to overcome the defect in the prior art that it is difficult to construct a face authentication model that can accurately identify human faces at a low cost, and provide a low-cost method that can accurately identify human faces. Face authentication model generation method, authentication method, device and storage medium of face authentication model

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Face authentication model generation method, authentication method, equipment and storage medium
  • Face authentication model generation method, authentication method, equipment and storage medium
  • Face authentication model generation method, authentication method, equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0061] This embodiment provides a method for generating a face authentication model, such as figure 1 As shown, the generation method includes the following steps:

[0062] Step 101. Obtain a first face authentication model.

[0063] Wherein, the first face authentication model includes a first face feature extraction module and a first classification matrix module. Data is input from the first human face feature extraction module, and the output of the first human face feature extraction module is used as the input of the first classification matrix module, and the first human face feature extraction module includes the first human face feature extraction parameter, and the first classification matrix module Include the first classification matrix parameter.

[0064] Specifically, the first face authentication model may be an existing face authentication model, or a face authentication model trained by itself based on an algorithm. No matter what kind of face authenticatio...

Embodiment 2

[0108] This embodiment provides a face authentication method, such as Figure 5 As shown, the face authentication method includes the following steps:

[0109] Step 201, acquiring a face image to be detected.

[0110] Wherein, the face image to be detected may be further preprocessed, and the specific preprocessing manner may refer to the corresponding manner in Embodiment 1, which will not be repeated here.

[0111] Step 202: Input the face image to be detected into the target face authentication model to obtain face authentication information.

[0112] Wherein, the target face authentication model is a model obtained according to the generation method of the face authentication model in Embodiment 1.

[0113] In this embodiment, accurate face authentication information can be obtained based on the target face authentication model, which greatly improves the accuracy of face recognition, especially for some specific scenarios, such as: the scene of verifying a child's face,...

Embodiment 3

[0115] The present invention also provides a generation device of a face authentication model, such as Image 6As shown, the generation device includes: a model acquisition module 301 , a training set acquisition module 302 , a first training module 303 and a second training module 304 .

[0116] The model acquisition module 301 is used to obtain the first face authentication model, the first face authentication model includes a first face feature extraction module and a first classification matrix module, data is input from the first face feature extraction module, and the first face feature extraction module is input from the first face feature extraction module. The output of the feature extraction module is used as the input of the first classification matrix module, the first human face feature extraction module includes the first human face feature extraction parameters, and the first classification matrix module includes the first classification matrix parameters;

[01...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a generation method of a face authentication model, an authentication method, equipment and a storage medium. The generation method comprises the following steps: acquiring a first face authentication model; obtaining a first training set; training the first face authentication model through the first training set to obtain a second face authentication model, and adjusting the first classification matrix parameter in the training process to obtain a second classification matrix module; and training the second face authentication model through the first training set to obtain a target face authentication model, adjusting the first face feature extraction parameter in the training process to obtain a second face feature extraction module, and adjusting the second classification matrix parameter to obtain a third classification matrix module. Compared with a mode of constructing a large-scale face data set at high cost, the face data set comprising a small number of face samples can be collected for a specific scene, integrated training is carried out, the model construction cost is reduced, the performance of the face authentication model in the specific scene is improved, and the error recognition rate is reduced.

Description

technical field [0001] The invention relates to the field of face authentication, in particular to a method for generating a face authentication model, an authentication method, a device and a storage medium. Background technique [0002] With the improvement of computer computing power, especially the specific floating-point operation acceleration of GPU (graphics processing unit, graphics processing unit) graphics card, and the massive training data brought by the development of the Internet, the use of neural network-based machine learning methods has been sufficient. It has achieved certain results in computer vision, natural language processing, and speech recognition. Among them, face recognition is an important application, and the method of deep convolutional neural network has also achieved better results than the traditional artificial feature method. In the scene of face comparison detection, there are two comparison requirements of 1:1 and 1:N. In 1:N compariso...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06V40/16G06V10/764G06V10/82G06V10/774G06N3/04G06N3/08G06K9/62
Inventor 王国权郝霖叶德建
Owner SHANGHAI CLEARTV CORP LTD