Unlock instant, AI-driven research and patent intelligence for your innovation.

Human face feature point data enhancement-based dynamic expression recognition method

A technology of facial expression recognition and facial features, applied in the field of dynamic facial expression recognition based on facial feature point data enhancement, can solve problems such as insufficient data, achieve accurate training results, increase the number of samples, and achieve accurate recognition results

Active Publication Date: 2020-11-13
西安云沃思网络科技有限公司
View PDF8 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, a problem has become more and more prominent, the lack of data

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
  • Human face feature point data enhancement-based dynamic expression recognition method
  • Human face feature point data enhancement-based dynamic expression recognition method
  • Human face feature point data enhancement-based dynamic expression recognition method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0046] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. The described embodiments are only part of the implementation of the present invention. example, not all examples. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts fall within the protection scope of the present invention.

[0047] Divide human facial expressions into 7 categories, namely: 0-angry, 1-disgust, 2-frightened, 3-happy, 4-sad, 5-surprised, 6-neutral. Due to the natural size relationship between digital codes, the model will be forced to learn this unnecessary constraint, resulting in model training errors. In order to eliminate this kind of error, the labels in this paper ado...

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 belongs to the field of human face dynamic expression recognition, and particularly relates to a human face feature point data enhancement-based dynamic expression recognition method, which comprises the steps of obtaining an original human face data set, and preprocessing the original human face data set to obtain a human face data training set, wherein the face data training set comprises an original face data set, an original trajectory diagram and a new trajectory diagram; inputting the training set into a constructed 3CNN model for model training; acquiring human face data in real time, and inputting the acquired human face data into the trained 3CNN model to obtain a human face dynamic expression recognition result. According to the method, the human face feature data is enhanced, so that enough data is provided for training the model when the convolutional neural network model is trained, and the finally obtained result is more accurate.

Description

technical field [0001] The invention belongs to the field of human face dynamic expression recognition, in particular to a dynamic expression recognition method based on human face feature point data enhancement. Background technique [0002] Facial Expression Recognition (FER), hereinafter referred to as FER. [0003] The study of facial expressions began in the 19th century. In 1872, in his famous treatise "The Expression of the Emotions in Animals and Man (The Expression of the Emotions in Animals and Man, 1872)", Darwin expounded the connection and difference between human facial expressions and animal facial expressions. In 1971, Ekman and Friesen did a pioneering work on the recognition of modern human facial expressions. They studied the six basic human expressions (ie, happiness, sadness, surprise, fear, anger, and disgust), determined the categories of recognition objects, and A facial expression image database consisting of thousands of different expressions has ...

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
CPCG06N3/08G06V40/168G06V40/172G06V40/174G06N3/047G06N3/048G06N3/045G06F18/241G06F18/2415
Inventor 钟福金黎敏尹妙慧王灵芝周睿丽赵建骅
Owner 西安云沃思网络科技有限公司