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

Face fusion recognition and identification method, target person information display method, early warning deployment and control method and system

A technology of face fusion and face recognition, which is applied in the field of face recognition, can solve the problems of resource occupation and large amount of computation, and achieve the effects of improving accuracy, less computation, and reducing recognition operations

Inactive Publication Date: 2019-07-02
深圳市星火电子工程公司
View PDF6 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although this method can make full use of the advantages of various "face comparison and recognition engines", improve the accuracy of face recognition and reduce the false positive rate, but the amount of calculation is too large, and each "face comparison and recognition engine" needs to It takes up too many resources to compare and identify each face picture individually, especially in our country where there are many people, and some public places have tens of thousands of people every day

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 fusion recognition and identification method, target person information display method, early warning deployment and control method and system
  • Face fusion recognition and identification method, target person information display method, early warning deployment and control method and system
  • Face fusion recognition and identification method, target person information display method, early warning deployment and control method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0039] Such as figure 1 As shown, a system comprising:

[0040] The front-end monitoring module is used to obtain the face image to be recognized, including at least one monitoring camera;

[0041] Integrated portrait recognition platform for face recognition, including at least two algorithm service providers, each algorithm service provider uses different face recognition algorithms for face recognition;

[0042] The face storage module is used to store the face image of the target person for comparison with the face image to be recognized, including at least one face library;

[0043] The back-end management center is used for accessing the front-end monitoring module, the fusion portrait recognition platform, the personnel database and the snapshot database, so as to dispatch each monitoring camera, each algorithm service provider and each face database.

[0044] Wherein, each face storehouse in the described face storage module is divided into by the source of face imag...

Embodiment 2

[0049] A face fusion recognition identification method, applied to the system described in Embodiment 1, such as figure 2 As shown, the steps include:

[0050] Send the face image to be recognized to one of the algorithm service providers for the first recognition, if the face image to be recognized passes the recognition, proceed to the next step;

[0051] Send the face image to be recognized to at least one other algorithm service provider for a second recognition, if the face image to be recognized is recognized by any other algorithm service provider, proceed to the next step;

[0052] If the algorithm service provider in the first recognition and any other algorithm service provider in the second recognition both recognize the face image to be recognized as the same target person, then the face image to be recognized will be identified as the corresponding target personnel.

[0053] The face fusion recognition identification method integrates multiple algorithm service...

Embodiment 3

[0063] A method for displaying target personnel information, applied to the system described in Embodiment 1, such as image 3 As shown, the steps include:

[0064] Using the face fusion recognition algorithm described in Embodiment 2, the same face image to be recognized is separately identified with the pre-recorded face image in the personnel database and the recognized face image in the snapshot library;

[0065] Invoking the identity information of the identified target personnel in the personnel database, and invoking the location information of the identified target personnel in the snapshot database;

[0066] The identified target person's identity information and location information will be displayed together.

[0067] In the target person information display method, the same face recognition image is identified separately in the person database and the snapshot database, and then the identified target person's identity information and location information are displ...

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 fusion identification method, which comprises the following steps of: sending a face image to be identified to one of algorithm service providers, carrying out first identification, and if the face image to be identified passes the identification, carrying out the next step; sending the to-be-identified face image to at least one other algorithm service provider forsecondary identification, and if the to-be-identified face image is identified by any one of the other algorithm service providers, performing the next step; and if the algorithm service provider in the first identification and any one of other algorithm service providers in the second identification identify the to-be-identified face image as the same target person, identifying the to-be-identified face image as the corresponding target person. The face fusion identification method not only fuses the algorithm advantages of all algorithm service providers, improves the accuracy of face identification, reduces the false alarm rate, but also has the advantage of small operand.

Description

technical field [0001] The invention relates to the field of face recognition, in particular to a face fusion recognition identification method, a target person information display method, an early warning deployment control method and a system. Background technique [0002] When the public security organs carry out early warning deployment and control, they need to take pictures of the flow of people through surveillance cameras to obtain face images to be recognized, and then perform face recognition on the face images to be recognized and the target personnel in the personnel database, and finally identify the successful target Personnel push to the police officers on duty, and the police officers on duty conduct on-site confirmation or arrest, but the face recognition algorithm of a single algorithm service provider often has more false positives, and the face recognition of different algorithm service providers Algorithms will have their own different algorithmic advant...

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): G06K9/00G06F16/532
CPCG06V40/166
Inventor 程力张映君
Owner 深圳市星火电子工程公司
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