Check patentability & draft patents in minutes with Patsnap Eureka AI!

A Facial Expression Recognition Method Based on Sample Weight Assignment and Deep Learning

A facial expression recognition and facial expression technology, applied in the field of image recognition, can solve problems such as the interference of facial expression categories and the inconsistency of emotion recognition complexity, so as to reduce overfitting, reduce interference, and increase robustness. Effect

Active Publication Date: 2021-03-23
HANGZHOU DIANZI UNIV
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to solve the problems of inconsistency in the complexity of emotion recognition and interference between facial expression categories due to the different expressions of people's emotions and the influence of uncontrolled environmental factors. Facial expression recognition method based on sample weight distribution and deep learning

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
  • A Facial Expression Recognition Method Based on Sample Weight Assignment and Deep Learning
  • A Facial Expression Recognition Method Based on Sample Weight Assignment and Deep Learning
  • A Facial Expression Recognition Method Based on Sample Weight Assignment and Deep Learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038] The present invention will be described in further detail below in conjunction with the accompanying drawings.

[0039] The present invention proposes a facial expression recognition method based on sample weight distribution and deep learning, and its overall block diagram is as follows: figure 1 As shown, it specifically includes the following four steps:

[0040] Step (1) Preprocessing of facial expression pictures. The specific operation is as follows:

[0041] The selected facial expression database is Fer2013. The database consists of 28709 training images, 3589 public testing images and 3589 private testing images. Each image is a grayscale image of 48×48 pixels. There are seven expressions in the Fer2013 dataset: Anger, Disgust, Fear, Happiness, Sadness, Surprise, and Neutral. This data set is the data of the Kaggle competition in 2013. Since it is mainly downloaded by using web crawlers, there are errors in the categories of some pictures.

[0042] The pr...

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 human facial expression recognition method based on sample weight distribution and deep learning. The present invention first obtains the preprocessed training set by cutting and performing random mirroring methods, and uses the VGG-11 network model to carry out k-fold cross-validation on the training set to obtain the weight parameter of each training sample, and in the recognition model During the establishment process, an adaptive Inception-Resnet network structure was designed, and the weight parameters of the training samples were used as the training parameters to design the loss function and optimize the recognition model. The present invention reduces the interference of abnormal samples to the network by proposing a data weight distribution method based on cross-validation, and designs an adaptive Inception-Resnet network, so that branches in the network can automatically adjust weights and reduce overfitting.

Description

technical field [0001] The invention belongs to the field of image recognition in computer applications, and in particular relates to a facial expression recognition method based on sample weight distribution and deep learning. Background technique [0002] In recent years, with the continuous development of artificial intelligence, people not only pay attention to the computer's powerful numerical calculation ability and data processing ability, but also pay more and more attention to the interaction between human and computer. As an important branch of face recognition, expression recognition is also flourishing under the attention of more and more scholars. Today, facial expression recognition is mostly used in scenarios of human-computer interaction such as multimedia, surveillance, and safe driving. Facial expressions can intuitively reflect human emotions, and computers can recognize various emotions through facial expressions. This will not only be of great help in u...

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 Patents(China)
IPC IPC(8): G06K9/00G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V40/174G06V40/172G06N3/045G06F18/214
Inventor 仇建胡焰焰沈方瑶商吉利张桦吴以凡戴国骏
Owner HANGZHOU DIANZI UNIV
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com