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

Face expression recognition method and device, equipment and medium

A facial expression recognition and facial expression technology, applied in the field of computer vision, can solve the problems of complex facial features and noise, low accuracy of facial expression recognition, etc., and achieve the effect of improving the accuracy.

Pending Publication Date: 2019-07-16
唐晓颖
View PDF15 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, there are more redundancy and noise in the facial features extracted based on the LDDMM-curve algorithm, resulting in a lower accuracy of facial expression recognition

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 expression recognition method and device, equipment and medium
  • Face expression recognition method and device, equipment and medium
  • Face expression recognition method and device, equipment and medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0032] figure 1 It is a flow chart of a facial expression recognition method provided by Embodiment 1 of the present invention. This embodiment is applicable to the situation of recognizing facial expressions, and the method can be executed by a facial expression recognition device, which can adopt It can be implemented by means of software or / and hardware, and can be configured in a device capable of performing facial expression recognition functions, such as a server.

[0033] Such as figure 1 As shown, the facial expression recognition method provided in this embodiment may include:

[0034] S110. Mark key points on each of the expression images in at least one expression image group, wherein each expression image group includes two images of different facial expressions of the same user.

[0035] The number of expression image groups is the number of samples collected for training the facial expression recognition model. The plurality of expression image groups may be e...

Embodiment 2

[0055] image 3 It is a flow chart of a facial expression recognition method provided by Embodiment 2 of the present invention. This embodiment optimizes and expands on the basis of the above embodiments, as image 3 As shown, the method may include:

[0056] S210. Mark the key points on each expression image in at least one expression image group, wherein each expression image group includes two images of different facial expressions of the same user.

[0057] S220. Based on each labeled expression image group, use a highly deformable Diffeomorphism metric mapping curve registration algorithm to extract an original feature set related to facial expressions.

[0058] S230. Use the original feature set to train the first support vector machine model, and calculate the weights of the features of each dimension in the original feature set after the training of the first support vector machine model is completed.

[0059] Given a set of training samples: {x i ,y i},x i ∈R d ...

Embodiment 3

[0091] Figure 4 It is a flow chart of a facial expression recognition method provided by Embodiment 3 of the present invention. This embodiment is optimized and extended on the basis of the above embodiments, such as Figure 4 As shown, the method includes:

[0092] S310. Mark the key points on each expression image in at least one expression image group, wherein each expression image group includes two images of different facial expressions of the same user.

[0093] S320. According to the position of each key point on each expression image in each expression image group, classify each key point on each expression image into a fourth preset number of curves, and discretize each curve Expressed.

[0094] S330. Use the discretized curve corresponding to any facial expression image in each facial expression image group as a source curve, and use the discretized curve corresponding to another remaining facial expression image as a target curve.

[0095] S340. In the Hilbert s...

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 embodiment of the invention discloses a facial expression recognition method and device, equipment and a medium, and the method comprises the steps: carrying out the marking of key points on eachexpression image in at least one expression image group, wherein each expression image group comprisse two images of different facial expressions of the same user; based on each marked expression image group, extracting an original feature set related to the facial expression by using a height deformation differential homoembryonic metric mapping curve registration algorithm; determining a targetfeature subset from the original feature set by using a support vector machine recursion feature elimination algorithm accompanying correlation deviation elimination; and training an identification model for identifying the facial expression based on the target feature subset. According to the embodiment of the invention, the method solves a problem that the facial expression recognition accuracyis relatively low due to the existence of relatively numerous redundant and noise in the extracted facial features in the existing method, and improves the facial expression recognition accuracy.

Description

technical field [0001] Embodiments of the present invention relate to the field of computer vision, and in particular to a method, device, device and medium for recognizing facial expressions. Background technique [0002] Facial expressions are an effective means of non-verbal communication. Facial expression recognition technology has important applications in the fields of human-computer interaction, intelligent control, security, medical treatment, communication and transportation. For example, by using cameras to capture customer pictures in shopping malls or stores, analyzing the facial expressions of customers, and interpreting the emotional information of customers, it is possible to determine the satisfaction of customers' consumption experience. [0003] At present, facial expression recognition methods are mainly based on the highly deformable Diffeomorphic Metric Mapping (LDDMM-curve) algorithm. However, there are many redundant and noisy facial features extract...

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): G06K9/00
CPCG06V40/168G06V40/174G06V40/172
Inventor 李晓舒唐晓颖
Owner 唐晓颖
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