Health supervision law enforcement illegal medical face recognition method based on deep learning

A technology of health supervision and deep learning, applied in the field of health supervision and law enforcement, can solve problems such as endangering people's lives and property, corrupting the image of the government and medical personnel, disrupting the order of the pharmaceutical market, etc., to promote accurate and efficient operation and improve work efficiency. , to avoid the effect of denial

Pending Publication Date: 2020-08-28
BEIJING MENGTIANMEN TECH
View PDF6 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, due to management omissions, some lawbreakers acted recklessly, engaged in medical activities without obtaining the qualifications of doctors, illegally practiced medicine and sold medicines, and defrauded people by all means, which seriously disrupted the order of the pharmaceutical market and endangered the lives and properties of the people. safety, tarnish the image of the government and medical personnel
Although the special rectification action against illegal medical practice has achieved initial results, the phenomenon of illegal medical practice is still widespread, and there is even a growing trend. Due to its strong mobility, it is not easy to be discovered by law enforcement agencies

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
  • Health supervision law enforcement illegal medical face recognition method based on deep learning
  • Health supervision law enforcement illegal medical face recognition method based on deep learning
  • Health supervision law enforcement illegal medical face recognition method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0036] The present invention illustrates the calculation process of the inventive method with a specific embodiment:

[0037] The photos uploaded by law enforcement officers in this example are as follows: Figure 4 shown;

[0038] The face detector detects the face information, and the detected face information is output to the face marker, and the marking result is as follows: Figure 5 shown;

[0039] The face feature extractor extracts the face feature data, and the face feature data is output to the face matcher, and the result of the facial feature mark is as follows: Image 6 As shown, the extraction result of the face feature extractor is:

[0040] -0.06459986418485641,0.09621178358793259,0.05518091470003128,-0.05910952389240265,-0.16387321054935455,-0.035034868866205215,-0.03379830718040466,-0.1451692134141922,0.1675742268562317,-0.1339283585548401,0.17521609365940094,-0.11801543831825256,-0.272583544254303,0.06244036182761192,-0.056363340467214584,0.16911481320858...

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 provides a health supervision law enforcement illegal medical face recognition method based on deep learning. The method comprises the steps that S10, creating a national illegal medicaldatabase based on illegal medical data in a health supervision law enforcement system; constructing a face detection model based on an SSD (Solid State Disk) Mobilenet V1 face detection deep learningmodel of TensorFlowJS; training the model to obtain the positions of the face holes in the image, extracting the data of the face feature points on the face holes in the detected face picture, and obtaining the confidence coefficient of the face feature points; taking the face feature points of which the confidence coefficients are higher than a threshold value as face mark boundary points, and obtaining coordinates of the face mark boundary points; and comparing the facial mark boundary points of the human face in the shot picture with the facial mark boundary points of the human face in theillegal medical database, and judging whether the person is an illegal medical person or not. The work efficiency of law enforcement officers is improved, and accurate and efficient operation of administrative law enforcement work is promoted.

Description

technical field [0001] The present invention relates to the field of health supervision and law enforcement, in particular to a deep learning-based face recognition method for illegal medical practitioners in health supervision and law enforcement. Background technique [0002] In recent years, with the continuous deepening of the reform of the medical and health system, the medical market has become more and more open, and the pattern of national unity has been broken. The society, the collective, and the individual set up hospitals in various ways, which solved the problem of people's difficulty in seeking medical treatment. However, due to management omissions, some lawbreakers acted boldly, engaged in medical activities without obtaining the qualifications of doctors, illegally practiced medicine and sold medicines, and defrauded people by all means, which seriously disrupted the order of the pharmaceutical market and endangered the lives and property of the people. Saf...

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): G06K9/00G06K9/46G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V40/169G06V40/172G06V40/161G06V10/454G06N3/045G06F18/22
Inventor 王锡辉丁学利徐宏伟
Owner BEIJING MENGTIANMEN TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products