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

Training method of face recognition model and online education system

A face recognition and training method technology, applied in the computer field, can solve the problems of data set training face recognition model, time-consuming and labor-intensive, etc.

Active Publication Date: 2021-02-05
深圳市海洋网络科技有限公司
View PDF11 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

But labeling data is a very time-consuming and labor-intensive job. For some units that lack manpower, it is difficult to use relatively large data sets to train face recognition models.

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
  • Training method of face recognition model and online education system
  • Training method of face recognition model and online education system
  • Training method of face recognition model and online education system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0042] An embodiment of the present invention provides a training method for a face recognition model, which is applied to an online education system, a financial system, and a human-computer interaction robot. The face recognition model includes a convolution structure and a supervision structure. Such as figure 1 As shown, the method includes:

[0043] S101: Obtain the training samples, where the training samples include marked human face images and unlabeled human face images.

[0044]S102: Perform down-sampling feature extraction operation on the training sample through the convolution structure to obtain a down-sampling feature set; perform up-sampling feature extraction on the down-sampling feature extraction corresponding to the unlabeled face image through the convolution structure to obtain up-sampling Feature set; the convolution structure performs unsupervised learning based on the downsampling feature set and the upsampling feature set, and the convolution structu...

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 training method of a face recognition model and an online education system, the face recognition model comprises a convolution structure and a supervision structure; after aself-encoding structure is introduced, unsupervised learning can be used, and samples do not need to be labeled during unsupervised learning training, so that a large amount of unlabeled data can be introduced, the labeled data volume is reduced, and the input data volume is improved. Meanwhile, since the self-encoding structure learns the features output in the convolution structure, the distinguishability of the feature vector (the feature vector finally output by the face recognition model) is improved during reverse transmission, and the distinguishing capability of the face recognition model for similar but different faces is improved, therefore, the face recognition model can greatly improve the accuracy of face recognition.

Description

technical field [0001] The invention relates to the field of computer technology, in particular to a training method for a face recognition model and an online education system. Background technique [0002] With the advancement of technology and the changes of the times, face recognition technology is widely used in finance, education and other fields, such as face payment in financial payment, identity recognition in online education, etc. [0003] Existing face recognition solutions based on machine learning require a large amount of data labeling. At present, a large part of the generalization ability of the model depends on the data used for model training. Generally, a larger amount of data allows the model to learn more Face invisible features, so as to improve the generalization ability of the model. The more data, the more face features the model learns. When using face recognition, use more face features such as eye size, eyebrow depth, and hole spacing Equivalenc...

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): G06K9/00G06N3/04G06N3/08
CPCG06N3/08G06V40/161G06V40/168G06N3/045
Inventor 姜培生
Owner 深圳市海洋网络科技有限公司