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

Mask face recognition method and system based on background filtering

A face recognition and background filtering technology, applied in the field of face recognition, can solve problems such as face recognition troubles

Pending Publication Date: 2020-10-23
SHENZHEN HEILS ZHONGCHENG TECH CO LTD
View PDF0 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

It is indeed a good idea to use the non-contact reporting mechanism of face recognition, but after testing by scientific research and engineering personnel, wearing a mask has caused huge troubles to face recognition, and puts forward a new test for the original algorithm.

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
  • Mask face recognition method and system based on background filtering
  • Mask face recognition method and system based on background filtering
  • Mask face recognition method and system based on background filtering

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0045] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative efforts fall within the protection scope of the present invention.

[0046] In order to solve the serious problem of difficult face recognition with masks, we designed a new module in the actual algorithm to reduce the interference of the background (including hair, masks, and areas other than the face) on the accuracy of the algorithm during face image preprocessing , let the algorithm pay attention to the feature extraction of the visible region of the face. Finally, the performance of the face recognition algorithm for mask occlusion is impr...

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 mask face recognition method and system based on background filtering, and the method comprises the steps of carrying out the preprocessing of a face image, and obtaining a face shielded image which comprises a mouth shielded image and an eye shielded image; based on the face image training and the data, training a first face recognition model used for recognizing that the face is not shielded, training a second face recognition model used for recognizing that the mouth is shielded, and training a third face recognition model used for recognizing that the eyes are shielded; performing facial feature vector fusion on the three types of face recognition models; and recognizing the human face by using the fused facial feature vector. According to the invention, interference of a background on algorithm precision is reduced during face image preprocessing, and the algorithm is enabled to pay attention to feature extraction of a face visible region; a plurality ofrecognition models are used for training and finally fusion is performed so that the recognition performance of the face recognition algorithm under the condition of face shielding can be enhanced.

Description

technical field [0001] The present invention relates to the technical field of face recognition, in particular to a face recognition method and system for face masks based on background filtering. Background technique [0002] Since 2020, affected by the 2019 novel coronavirus, the whole country has entered a state of emergency epidemic prevention. In order to prevent the spread of pathogens, everyone is required to wear masks, wash hands frequently, and go out less. However, the resumption of work is also urgent. During the resumption of work, it is also necessary to closely observe people's physical conditions, find suspicious symptoms, and be able to be controlled in time. However, if this large-scale task is completely handled by relevant staff, it may fall into an embarrassing situation of insufficient staff. . [0003] Therefore, a standardized temperature measurement and supervision process is essential. It is indeed a good idea to use the non-contact reporting mec...

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
IPC IPC(8): G06K9/00G06K9/62
CPCG06V40/161G06V40/168G06V40/172G06F18/214
Inventor 杨泽霖杨坚涂前彦刘伟生薛利荣
Owner SHENZHEN HEILS ZHONGCHENG TECH CO LTD
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