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

Facial expression recognition method and device based on zero sample learning

A facial expression recognition and facial expression technology, applied in the field of computer vision, can solve the problems of poor training data quality, reduce repetitive work, and insufficient facial expression training data, so as to improve accuracy, reduce repetitive work, Solve the effect of insufficient training data

Pending Publication Date: 2022-01-11
GUANGDONG POLYTECHNIC NORMAL UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to overcome the deficiencies of the prior art. The present invention provides a method and device for recognizing facial expressions based on zero-sample learning, which can stably and quickly identify the type of facial expression corresponding to a human face image, reducing repetition work; and there is no need for relevant sample training to solve the problems of insufficient training data and poor quality of training data for facial expressions

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
  • Facial expression recognition method and device based on zero sample learning
  • Facial expression recognition method and device based on zero sample learning
  • Facial expression recognition method and device based on zero sample learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0052] see figure 1 , figure 1 It is a schematic flow chart of the facial expression recognition method based on zero-shot learning in the embodiment of the present invention.

[0053] Such as figure 1Shown, a kind of facial expression recognition method based on zero sample learning, described method comprises:

[0054] S11: receiving an input face image, and extracting image features of the face image based on a deep neural network model;

[0055] In the specific implementation process of the present invention, the receiving the input face image includes: receiving the captured image collected by the image capturing device, and inputting the captured image into the target detection network model for face detection, and cutting out the captured image The face area image in , the size of the face area image is 224*224; image color normalization processing is performed on the face area image, and an input face image is formed.

[0056] Further, the deep neural network model...

Embodiment 2

[0099] see figure 2 , figure 2 It is a schematic diagram of the structural composition of the facial expression recognition device based on zero-shot learning in the embodiment of the present invention.

[0100] Such as figure 2 Shown, a kind of facial expression recognition device based on zero sample learning, said device comprises:

[0101] Feature extraction module 21: for receiving the face image of input, and extract the image feature of described face image based on deep neural network model;

[0102] In the specific implementation process of the present invention, the receiving the input face image includes: receiving the captured image collected by the image capturing device, and inputting the captured image into the target detection network model for face detection, and cutting out the captured image The face area image in , the size of the face area image is 224*224; image color normalization processing is performed on the face area image, and an input face im...

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 facial expression recognition method and device based on zero sample learning, and the method comprises the steps: receiving an input facial image, and extracting the image features of the facial image based on a deep neural network model; converting the image features into image semantic vectors; extracting attribute text information corresponding to various facial expressions from a database, and converting the attribute text information into attribute semantic vectors; calculating the similarity between the image semantic vector and the attribute semantic vector corresponding to each facial expression to obtain a similarity calculation result; the facial expression type corresponding to the maximum similarity in the similarity calculation result being the facial expression type corresponding to the facial image. In the embodiment of the invention, the facial expression type corresponding to the facial image can be recognized stably and quickly, and repeated work is reduced; and related sample training is not needed, so that the problems of insufficient facial expression training data and poor training data quality are solved.

Description

technical field [0001] The invention relates to the technical field of computer vision, in particular to a method and device for recognizing facial expressions based on zero-sample learning. Background technique [0002] In human's daily communication, expression is the way to convey the most information, accounting for 55%, much higher than voice (38%) and language (7%). Although the internal mechanism of the brain's control of facial expressions is not yet clear, facial expressions are a characteristic of the brain state, which can last for a period of time after the stimulus that induces facial expressions disappears, so facial expressions are recognizable. At present, facial expression recognition is the core of human-computer interaction, and it is widely used, such as intelligent companion robot to realize human-computer emotional communication; smart classroom, to determine the emotional state of students in learning; intelligent driving, to determine the emotional st...

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): G06V40/16G06V10/44G06V10/82G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06N3/045G06F18/241
Inventor 李辉辉肖湘玲郭建华刘晓勇
Owner GUANGDONG POLYTECHNIC NORMAL 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