Expression recognition method based on multi-branch cross-connection convolutional neural network

A technology of convolutional neural network and expression recognition, which is applied in the field of expression recognition based on multi-branch cross-connection convolutional neural network, can solve the problems of incomplete feature extraction, waste of resources, and low efficiency, so as to improve the ability of feature extraction and improve Performance, Effects of Effective Image Feature Extraction

Active Publication Date: 2020-09-08
QIQIHAR UNIVERSITY
View PDF6 Cites 16 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to solve the problems of low efficiency, serious resource waste and incomplete feature extraction in the existing traditional expression feature extraction method, and propose an expression recognition method based on multi-branch cross-connection convolutional 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
  • Expression recognition method based on multi-branch cross-connection convolutional neural network
  • Expression recognition method based on multi-branch cross-connection convolutional neural network
  • Expression recognition method based on multi-branch cross-connection convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0015] Specific implementation mode 1: The specific process of the facial expression recognition method based on multi-branch cross-connection convolutional neural network in this implementation mode is as follows:

[0016] Expression recognition is a classic research topic in the field of computer vision. Existing expression recognition methods can be roughly divided into three categories: expression recognition based on traditional methods, expression recognition based on convolutional neural networks, and expression recognition methods based on fusion of traditional methods and convolutional neural networks.

[0017] For expression recognition based on traditional methods, handcrafted features such as Gabor wavelet coefficients [16] (TianYL, Cohn J F.Evaluation of Gabor-Wavelet-Based Facial Action Unit Recognition in Image Sequences of Increasing Complexity[C] / / Automatic Face and GestureRecognition,2002.Proceedings.Fifth IEEE International Conference on.IEEE,2002.), local ...

specific Embodiment approach 2

[0027] Specific embodiment two: the difference between this embodiment and specific embodiment one is: in the described step one, the facial expression image data set is preprocessed; the specific process is:

[0028] Select Fer2013 and CK+ facial expression data sets, normalize the facial expression data sets, and perform data enhancement on the normalized data;

[0029] The process of data augmentation on the normalized data is as follows:

[0030] Randomly zoom, flip, translate, and rotate the normalized data;

[0031] Other steps and parameters are the same as those in Embodiment 1.

specific Embodiment approach 3

[0032] Specific embodiment three: what this embodiment is different from specific embodiment one or two is: build multi-branch cross-connection convolutional neural network (MBCC-CNN) in described step 2, be used to extract facial expression image feature; Concrete process for:

[0033] The multi-branch cross-connection convolutional neural network consists of the first convolutional layer, module 1, module 2 and module 3, the fortieth convolutional layer, batch normalization BN (BatchNormalization) and Relu activation function;

[0034] Module 1 includes a second convolutional layer, a third convolutional layer, and a fourth convolutional layer, a twenty-first convolutional layer, a twenty-second convolutional layer, and a twenty-third convolutional layer;

[0035] The image data of the face dataset is the input layer, the input layer data is input to the first convolutional layer, the output data of the first convolutional layer is respectively input into the second convolut...

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 relates to an expression recognition method, in particular to an expression recognition method based on a multi-branch cross-connection convolutional neural network. The invention aims to solve the problems of low efficiency, serious resource waste and incomplete feature extraction of an existing traditional expression feature extraction method. The method comprises the following steps of: 1, preprocessing a facial expression image data set; 2, a multi-branch cross-connection convolutional neural network is constructed and used for extracting facial expression image features, andthe process is as follows: the multi-branch cross-connection convolutional neural network is composed of a first convolutional layer, a module 1, a module 2, a module 3, a forty-th convolutional layer, a batch standardization BN and a Relu activation function; and 3, classifying the image features extracted by the network by adopting a Softmax classification algorithm, namely connecting a globalmean value pooling after the constructed multi-branch cross-connection convolutional neural network, and carrying out multi-classification by using a Softmax function after a global mean value poolinglayer. The method is applied to the field of expression recognition.

Description

technical field [0001] The invention relates to a facial expression recognition method. Background technique [0002] Facial Expression Recognition (FER) mainly predicts basic facial expressions through changes in the appearance of the face. Facial expression is the most direct and effective mode of emotion recognition [1][2] ([1]C.Darwin and P.Prodger,The expression of the emotions in man and animals.Oxford University Press,USA,1998.[2]Y.-I.Tian,T.Kanade,and J.F.Cohn,“Recognizing action units for facial expression analysis,” IEEE Transactions on pattern analysis and machine intelligence, vol.23, no.2, pp.97–115, 2001.), facial expression recognition is an important branch of face recognition, it has many aspects of human-computer interaction applications, such as fatigue driving detection and real-time expression recognition on mobile phones. At the same time, it also has important developments in various fields such as education monitoring and medical testing. [3-5] ([...

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): G06K9/00G06N3/04
CPCG06V40/172G06V40/168G06V40/174G06N3/045
Inventor 石翠萍谭聪靳展苗凤娟刘文礼
Owner QIQIHAR UNIVERSITY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap