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

Face recognition method and system

A technology for face recognition and to-be-recognized, which is applied in the field of face recognition to achieve the effects of improving recognition accuracy, ensuring migration, and reducing labor costs

Active Publication Date: 2021-06-01
湖南视觉伟业智能科技有限公司
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The invention provides a face recognition method and system to solve the technical problems of the existing face recognition methods

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 recognition method and system
  • Face recognition method and system
  • Face recognition method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0038] Such as figure 1 As shown, the present invention discloses a face recognition method, comprising the following steps:

[0039] Obtain the face image to be recognized and the comparison face images of multiple known identities;

[0040] Using a distributed computing framework to classify the features of the comparison face images, and calculate / update the class center sample features of the comparison face features of each category;

[0041] Extracting face features from the face image, performing similarity matching between the face features and a plurality of different categories of center sample features, and judging the identity of the face according to the similarity matching results.

[0042] In addition, this embodiment also discloses a computer system, including a memory, a processor, and a computer program stored in the memory and operable on the processor. When the processor executes the computer program, the above method is implemented. step.

[0043] In t...

Embodiment 2

[0045] The second embodiment is an extended embodiment of the embodiment, and its difference from the first embodiment is that the structure and functions of the face recognition system are refined, specifically including:

[0046] In this example, if Figure 7 As shown, a community face recognition system and equipment based on a class center are disclosed. The system consists of two parts, including an embedded front-end subsystem and a private cloud service subsystem. The embedded front-end subsystem realizes the three major functions of face detection, face recognition and access control; the private cloud service subsystem includes the functions of face feature center calculation and face feature base database update.

[0047] Among them, such as image 3 As shown, the embedded front-end subsystem includes:

[0048] An image acquisition module, configured to acquire camera images;

[0049] A face detection module for detecting faces in an image;

[0050] The image quali...

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 face recognition method and system. By acquiring a face image to be recognized and a plurality of contrasting face images of known identities; using a distributed computing framework to classify the features of the contrasting face images, and Calculating / updating the class center sample features of the comparative face features of each category; extracting face features from the face image, and performing similarity matching between the face features and the class center sample features of multiple different categories , and judge the identity of the face according to the result of the similarity matching, and use the distributed computing framework to calculate and update the center features of the face, which can improve the system's ability to calculate the center of the large-scale face features, and then more quickly face recognition.

Description

technical field [0001] The invention relates to the field of face recognition, in particular to a face recognition method and system. Background technique [0002] In recent years, with the development of artificial intelligence, the accuracy of face recognition has been greatly improved, making this technology widely used in social life, including face recognition access control, face payment, face attendance, and identity authentication. Deep learning technology is currently an important means to achieve high-precision face recognition. By designing a better neural network structure and a better loss function, a high-precision face recognition model can be obtained. The improvement of GPU performance and the emergence of large-scale open face datasets also provide strong support for the training of high-precision face algorithm models. [0003] Face recognition under unconstrained conditions still has some problems, such as large gesture recognition, cross-age recognition...

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): G06K9/00G06N3/04
CPCG06V40/168G06V40/172G06N3/045
Inventor 夏东黎佳志
Owner 湖南视觉伟业智能科技有限公司
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com