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

Fast expression recognition algorithm and system based on double-model probability optimization

An optimization algorithm and facial expression recognition technology, applied in character and pattern recognition, biological neural network model, acquisition/recognition of facial features, etc. Effects of Computational and Storage Costs

Active Publication Date: 2021-05-25
QINGDAO UNIV
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The focus of this invention is to adjust the structure and parameters of the neural network, which can effectively recognize painful expressions, but once the neural network is trained, the accuracy cannot be adjusted, which is due to the uncertainty in the training process of the neural network

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
  • Fast expression recognition algorithm and system based on double-model probability optimization
  • Fast expression recognition algorithm and system based on double-model probability optimization
  • Fast expression recognition algorithm and system based on double-model probability optimization

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0069] A fast expression recognition algorithm based on dual-model probability optimization,

[0070] Step 1: Frame the image sent by the camera, cut out the face image, and use it as a standard image;

[0071] Through the library function provided by opencv, the video frame is sent to the Haar face cascade device, the face in the image is retrieved through the classifier, and the face is cut into a standard image of (224,224) to prepare for image preprocessing;

[0072] Step 2 performs binarization preprocessing on the standard image, and at the same time performs median filtering to reduce the interference of invalid features to obtain a binary image;

[0073] The standard image is grayscaled and binarized. At the same time, in order to reduce the influence of irrelevant features such as beards and spots, the median filter algorithm is used to denoise the image;

[0074] Step 3 Send the standard image and the binary image to the Mini_Xception model and the CNN7 model for pa...

Embodiment 1

[0080] The experimental results of Example 1 are shown in Table 1.

[0081] Table 1 Algorithm 1 Experimental Results

[0082]

[0083] Acc represents the overall recognition accuracy of facial expressions.

Embodiment 2

[0085] A fast expression recognition algorithm based on dual-model probability optimization,

[0086] Step 1: Frame the image sent by the camera, cut out the face image, and use it as a standard image;

[0087] Through the library function provided by opencv, the video frame is sent to the Haar face cascade, the face in the image is retrieved through the classifier, and the face is cut into a standard image of (224,224) to prepare for image preprocessing;

[0088] Step 2 performs binarization preprocessing on the standard image, and at the same time performs median filtering to reduce the interference of invalid features to obtain a binary image;

[0089] The standard image is grayscaled and binarized. At the same time, in order to reduce the influence of irrelevant features such as beards and spots, the median filter algorithm is used to denoise the image;

[0090] Step 3 Send the standard image and the binary image to the Mini_Xception model and the CNN7 model for parallel ...

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 fast expression recognition algorithm and system based on dual-model probability optimization. The system mainly comprises a face recognition cutting module, an image preprocessing module, a dual-model prediction module and a combined probability optimization module. An image is input for intercepting a human face, binarization processing is carried out, the human face is respectively sent to a double-model classifier trained by a standard image and a binarized image for parallel judgment, and meanwhile two optimization algorithms are provided to carry out combined probability optimization on double-model output results. Thus, high-accuracy judgment and recognition are realized by utilizing probability optimization of recognition results of two lightweight neural network models with low accuracy. According to the invention, the pain recognition rate of continuous threshold time and above can be not lower than 99%, the calculation cost and the storage cost are greatly reduced, and meanwhile, other types of expressions can be effectively recognized.

Description

technical field [0001] The invention belongs to the field of image processing and emotion recognition, in particular to a fast expression recognition algorithm and system based on dual-model probability optimization. Background technique [0002] With the development of society, people are paying more and more attention to acute diseases. Due to the rapid onset of acute diseases, severe symptoms and rapid changes, it is difficult to effectively prevent acute diseases and the onset is often accompanied by severe pain. Unable to call for help, unable to obtain timely medical treatment, the patient's life is greatly threatened. At present, for the identification of acute attacks, it is common to use personnel escorts, video surveillance, or install specific sensor devices on the patient's body, which causes a waste of human resources and inconveniences the patient's movement. Although the existing neural network has a very high The accuracy rate is high, but the storage and ca...

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): G06K9/00G06K9/62G06N3/04G06N3/08
CPCG06N3/084G06V40/174G06V40/172G06N3/047G06N3/048G06N3/045G06F18/2415G06F18/214
Inventor 李宪李炎潘亚磊杨明业于继宇
Owner QINGDAO 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