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

A method for improving face recognition accuracy and traffic speed

A face recognition and accuracy technology, applied in the field of face recognition, can solve the problems of the size of the recognition model, the limited feature dimension, the reduction of recognition accuracy and traffic speed, etc., and achieve the effect of improving recognition accuracy and reducing interference

Active Publication Date: 2021-11-26
UNIVERSAL UBIQUITOUS TECH CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In actual use, due to these interference factors, a person may need multiple identifications to pass, which greatly reduces the identification accuracy and passing speed
Moreover, in order to quickly obtain recognition results on embedded devices, the size and feature dimensions of the recognition model trained by the neural network are limited.

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
  • A method for improving face recognition accuracy and traffic speed

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0019] The present invention will be further described below in conjunction with accompanying drawing.

[0020] Such as figure 1 As shown, when a user uses face recognition technology to verify their identity, ideally, the registration photos of the user and all personnel in the bottom library have the maximum comparison score obtained in the recognition model A, that is, the top1 score satisfies: Score_top1≥Th, Th It is the preset identification threshold, indicating that the user has passed the identification, and at the same time indicates that the user's identity is the identity of the person whose registration photo corresponds to the top1 score. If at this time, Score_top1≤Th1, Th1>Th, Th1 is set by the user, which means that the user has passed the identification, and at the same time, the similarity between the user's bottom library photo and the current real person is not particularly high. At this time, add or update the live photo of this period as The replacement ...

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 method for improving the accuracy rate and traffic speed of face recognition, which includes the following steps: the maximum value of the comparison score obtained in the recognition model A of the registered photos of the user and all personnel in the bottom library, that is, the top1 score satisfies: Score_top1 ≥Th, Th is the preset recognition threshold, indicating that the user has passed the recognition; if at this time, Score_top1≤Th1, Th1>Th, Th1 is set by the user, it means that the user has passed the recognition and the similarity difference between the user's bottom library photo and the current real person Larger, add or update the on-site photo of this period as a replacement photo and add it to the user's face database.

Description

technical field [0001] The invention relates to the field of face recognition, in particular to a method for improving the accuracy and speed of face recognition. Background technique [0002] Face recognition will be affected by different factors in actual use scenarios, including light, registration photos, camera installation height, etc. These uncontrolled factors will affect the speed and accuracy of face recognition. In actual use, these interfering factors will generally reduce the accuracy of face recognition, making it difficult to identify the person being tested. [0003] The face recognition verification score is not always a full score, which is due to the difference between the actual use environment and the style of the registration photo (such as the registration photo being p-picture, beautified, beautified, etc.), the registration photo of the tested person and the time when passing through the device. There are factors such as age difference, different l...

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 Patents(China)
IPC IPC(8): G06K9/00G06K9/62
CPCG06V40/161G06F18/22
Inventor 郑东赵拯赵五岳
Owner UNIVERSAL UBIQUITOUS TECH CO LTD