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

Method for identifying drug addiction attack of a drug addict based on facial expression feature analysis

A feature analysis and facial expression technology, applied in the field of face recognition, can solve problems such as the inability of manual management to accurately monitor drug users, increase the difficulty of management in drug rehabilitation centers, and endanger life and health, so as to improve real-time computing efficiency and good Classification effect and generalization ability, effect of providing judgment accuracy

Active Publication Date: 2021-07-16
GUANGZHOU UNIVERSITY
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] The management of drug rehabilitation centers is becoming more and more difficult. Manual management methods cannot accurately monitor every drug user. When drug addicts attack their drug addiction, they may not be detected in time and no protective measures will be implemented, thus endangering their lives and health.

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
  • Method for identifying drug addiction attack of a drug addict based on facial expression feature analysis
  • Method for identifying drug addiction attack of a drug addict based on facial expression feature analysis
  • Method for identifying drug addiction attack of a drug addict based on facial expression feature analysis

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0056] Such as figure 1 As shown, the present embodiment provides a method for identifying drug addicts' drug addiction attacks based on facial expression feature analysis, including the following steps:

[0057] S1: Collect the video of the person being monitored through a high-definition camera, and perform face recognition on the image in the video:

[0058] In this embodiment, the image of the person being monitored is acquired in the video, the Haar-like features in the image are extracted, and the real-time computing efficiency is improved in combination with the integral image method; Face image location.

[0059] S2: Perform image preprocessing on the extracted face image. The image preprocessing steps include: image grayscale, histogram equalization, Gaussian filtering, and image scaling. During the image scaling process, the size of the image is enlarged Using a bilinear interpolation algorithm, a preprocessed face image of consistent size is finally obtained.

[...

Embodiment 2

[0090] The present embodiment provides a drug addict seizure recognition system based on facial expression feature analysis, including: collection and recognition module, image preprocessing module, neural network construction module, neural network training module, feature extraction module and judgment output module;

[0091] The collection and recognition module is used to collect the video of the person being monitored, and perform face recognition on the image in the video;

[0092] The image preprocessing module is used to perform image preprocessing on the extracted face image;

[0093] Described neural network construction module is used for constructing DNN deep neural network, and described DNN deep neural network comprises input layer, convolution layer, pooling layer, GRU layer and Softmax output layer connected successively;

[0094] The neural network training module is used for network training, the hyperparameter value of the DNN deep neural network to be train...

Embodiment 3

[0098] This embodiment provides a storage medium, the storage medium can be a storage medium such as ROM, RAM, magnetic disk, optical disk, etc., and the storage medium stores one or more programs. A method for identifying drug addiction episodes in drug users based on facial expression feature analysis.

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 method for identifying drug addiction attack of a drug addict based on facial expression feature analysis. The method comprises the following steps: acquiring a video of a monitored person and performing facial identification; preprocessing the extracted face image; constructing a DNN deep neural network and performing network training, setting a hyper-parameter value of a to-be-trained DNN deep neural network, and inputting the training set sample into the DNN deep neural network for training; wherein the DNN deep neural network comprises an input layer, a convolutional layer, a pooling layer, a GRU layer and a Softmax output layer which are connected in sequence; inputting the face image after image preprocessing into the trained DNN deep neural network, extracting features of the face image, and outputting a predicted value of the drug addiction attack probability; and when the predicted value of the output drug addiction attack probability is greater than a preset threshold value, determining that the monitored person has the drug addiction attack. Judgment accuracy is improved, and good classification effect and generalization ability are achieved.

Description

technical field [0001] The invention relates to the technical field of face recognition, in particular to a method for identifying drug addiction attacks of drug addicts based on facial expression feature analysis. Background technique [0002] The management of drug rehabilitation centers is becoming more and more difficult. Manual management methods cannot accurately monitor every drug user. When drug addicts attack their drug addiction, they may not be detected in time and no protective measures will be implemented, thus endangering their lives and health. . Using the facial expression characteristics of drug addicts such as facial spasms and listlessness to identify the behavior of drug addiction attacks and provide intelligent and automatic management methods for drug rehabilitation centers has become the key to improving the management capabilities and work efficiency of drug rehabilitation centers. Contents of the invention [0003] In order to overcome the defects...

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): G06K9/00G06K9/62G06N3/04G06N3/08
CPCG06N3/084G06V40/168G06V40/174G06V40/172G06V20/41G06N3/047G06N3/045G06F18/2148G06F18/2415
Inventor 朱静李楚宪牛子晗明家辉钟绮岚杜晓楠尹邦政赵宣博伍冯洁王茹皓
Owner GUANGZHOU UNIVERSITY
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