Expression recognition method based on lightweight convolutional neural network

A convolutional neural network and expression recognition technology, applied in the field of computer vision, can solve problems such as deepening the model, excessive model parameters, and unfavorable model training and practical application.

Active Publication Date: 2020-05-15
BEIJING UNIV OF CIVIL ENG & ARCHITECTURE
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in order to obtain higher accuracy, scholars continue to deepen the depth of the model, resulting in too many model parameters
This is not conducive to the training of the model and the use of practical applications

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 lightweight convolutional neural network
  • Expression recognition method based on lightweight convolutional neural network
  • Expression recognition method based on lightweight convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0053] This embodiment provides an expression recognition method based on a lightweight convolutional neural network.

[0054] like figure 1 As shown, an expression recognition method based on a lightweight convolutional neural network provided in this embodiment includes four parts: inputting a single frame image, face detection, face correction, and expression recognition. Starting from the original input image, after two stages of image processing, it then predicts the classification of facial expressions.

[0055] The light weight of this embodiment refers to a convolutional network calculation method that is more efficient and requires less calculation than standard convolutional calculations, thereby reducing the computational complexity of the convolutional network and improving operational efficiency. Dense blocks refer to the number of convolutional networks. Within a certain range, the larger the number of convolutional networks, the higher the accuracy of the model...

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 the field of artificial intelligence, and provides an expression recognition method based on an lightweight convolutional neural network. The method is characterized by comprising the steps: S1, building and training a lightweight convolutional network model, wherein the convolution layer number range of the lightweight convolutional network model is 36-58, the grouping convolution group number range of the lightweight convolutional network model is 2-4, and the compression layer compression factor range of the lightweight convolutional network model is 0.3-0.5; s2, building a face corrector; s3, detecting and correcting the input image by adopting a face corrector to obtain a preprocessed image; and S4, adopting a lightweight convolutional neural network model toclassify and pre-process the facial expressions in the image. According to the invention, the technical problems of low recognition accuracy and low recognition speed in the prior art are solved, andhigh real-time performance is achieved while the accuracy is ensured.

Description

technical field [0001] The invention relates to the field of computer vision, in particular to an expression recognition method based on a lightweight convolutional neural network. Background technique [0002] Emotion is a cognitive experience produced by human beings under strong psychological activities, and it is an important element that guides communication in social environments. Emotions can be triggered by a variety of sources, including mood, personality, motivation, etc. As a unique signal transmission system, facial expression can express people's psychological state and is one of the effective methods for analyzing emotions. Expression recognition mainly has the following four processes: face positioning, face correction, feature extraction and expression classification. Feature extraction and expression classification, as an important part of the process, are the core difficulties of expression recognition. Traditional methods use hand-designed geometric fea...

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): G06K9/00G06K9/46G06K9/62G06N3/04G06N3/08G06T5/00
CPCG06N3/08G06T5/006G06T2207/10004G06T2207/20081G06T2207/20084G06T2207/30201G06V40/168G06V40/174G06V10/50G06N3/045G06F18/2411G06F18/214
Inventor 赵光哲张雷杨瀚霆朱娜邵帅田军伟
Owner BEIJING UNIV OF CIVIL ENG & ARCHITECTURE
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