Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Facial recognition method and system for face masks

A face recognition and mask technology, applied in the field of pattern recognition, can solve the problem of face recognition data sets without masks, and achieve the effect of alleviating the shortage

Active Publication Date: 2020-07-28
WUHAN UNIV
View PDF5 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, there is currently no publicly available large-scale mask face recognition dataset. To this end, it is necessary to build a large-scale mask face sample set matching the model to drive model training and iterative optimization.

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
  • Facial recognition method and system for face masks
  • Facial recognition method and system for face masks
  • Facial recognition method and system for face masks

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0040] In order to facilitate those of ordinary skill in the art to understand and implement the present invention, the present invention will be described in further detail below in conjunction with the accompanying drawings and examples of implementation. It should be understood that the implementation examples described here are only used to illustrate and explain the present invention, and are not intended to limit this invention.

[0041] please see figure 1 , a kind of mask face recognition method provided by the invention, comprises the following steps:

[0042] Step 1: Use the open source ArcFace face recognition model as the baseline model to build a mask face recognition deep learning model;

[0043] Specifically include the following sub-steps:

[0044] Step 1.1: Eyebrow extraction;

[0045] The open source Face-Alignment algorithm is used to extract the feature points of eyebrows and eyes, and the feature points of eyebrows and eyes are sequentially connected in...

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 facial recognition method and system for face masks and the method comprises the steps: building a face-eyebrow multi-granularity recognition model based on ArcFace, and improving the mask face recognition effect through employing an eyebrow fine feature structure. For the current situation that a facial recognition data set training model for face masks is urgently needed at present, multiple face data set construction methods for face masks are provided; on this basis, a complete mask face recognition system is formed, and the system comprises three main links of model construction, model training and face recognition. The facial recognition precision is remarkably improved, and the established data set effectively supports the technical development so that themask faces can cover faces.

Description

technical field [0001] The invention belongs to the technical field of pattern recognition, and relates to a face recognition method and system, in particular to a mask face recognition method and system. [0002] technical background [0003] During the COVID-19 epidemic, all people wear masks, and face recognition technology, which is an important means of identity verification, basically fails, which poses a huge obstacle to the application of face identity authentication, including community access management, face access control and attendance, and face face gates at stations. and other application scenarios. Especially in public security inspection places such as railway stations, people who wear masks do not recognize the face gates, and take off the masks to pass through the gates, and there is a risk of infection; there are also non-contact access control applications, due to the contact transmission of viruses, passwords or fingerprints. For the risk of virus infec...

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): G06K9/00G06K9/62
CPCG06V40/171G06V40/172G06F18/214Y02T10/40
Inventor 王中元黄宝金王光成熊张洋洪琪吴浩易鹏
Owner WUHAN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com