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

Expression recognition method based on face block

A facial expression recognition and facial technology, applied in the field of computer vision, can solve the problems of inaccurate recognition results, only consider the overall characteristics of facial images, and ignore the connection of facial movement muscle blocks, etc., so as to improve accuracy and robustness Effect

Pending Publication Date: 2022-01-14
NANJING UNIV
View PDF0 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0011] The problem to be solved by the present invention is: most of the existing facial expression recognition methods are based on frontal face images, only considering the overall features of the facial pictures, ignoring the connection between the facial movement muscles closely related to the facial expressions, thus The recognition result is not accurate enough

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
  • Expression recognition method based on face block
  • Expression recognition method based on face block
  • Expression recognition method based on face block

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0029] The present invention proposes a facial expression recognition method based on facial blocks. By constructing two small complementary networks and fusing facial features at different levels, the result of classifying six basic expressions is obtained.

[0030] The present invention comprises the following steps: 1) Constructing a fully convolutional facial expression recognition network using face blocks: the network includes three stages of data preprocessing, facial feature extraction stage, and comprehensive prediction stage, wherein the facial feature extraction stage uses two complementary volumes One of them is an expression recognition network based on the time information of the picture, which is used to extract the overall features of the entire face, and the other is an expression recognition network based on the geometric information of the picture, which is used to extract the local features of the face block; 2) Training stage : Use the expression recognitio...

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

An expression recognition method based on face block comprises the following steps: 1) using the face block to construct a fully convolutional expression recognition network, in a face feature extraction stage: adopting two complementary convolutional networks, wherein one is an expression recognition network based on picture time information for extracting overall features of a whole face, and the other one is an expression recognition network that is used for extracting local features of the face blocks based on picture geometric information; 2) a training stage: training a network by using an expression recognition data set, using a cross entropy function as a loss function, and adopting an online difficult sample retraining strategy in the process; and 3) a test stage: inputting the test image into the network to obtain an expression recognition result. In the feature extraction stage, picture information and face key point information are fully utilized, two complementary small networks are constructed, the overall features of the face and the local features of the face blocks are extracted, and the robustness of face expression recognition is improved.

Description

technical field [0001] The invention belongs to the technical field of computer vision, relates to image recognition in multimedia technology, and is an expression recognition method based on face blocks. [0002] technical background [0003] Expression recognition is a given still face image or dynamic face image sequence, the system can determine the facial expressions of one or more people in the image. Therefore, the expression recognition system can be roughly divided into two categories, one is the static image expression recognition system, and the other is the dynamic sequence expression recognition system. In the static image expression recognition system, the network only considers the geometric characteristics of a single image, but the dynamic sequence expression recognition system also considers the temporal characteristics of related frames. The specific research content of facial expression recognition system includes face detection, facial expression feature...

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): G06V40/16G06V10/80G06V10/82G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06N3/048G06N3/045G06F18/25
Inventor 武港山王丽
Owner NANJING UNIV