Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Semi-supervised learning facial expression recognition method based on fuzzy training samples

A technology of facial expression recognition and semi-supervised learning, which is applied in character and pattern recognition, acquisition/recognition of facial features, instruments, etc., and can solve the problem that unmarked expression image data cannot be used

Active Publication Date: 2016-11-09
ZHEJIANG UNIV
View PDF5 Cites 42 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The purpose of the present invention is to provide a semi-automation method based on fuzzy training samples to solve the problem that a large amount of marked training data is required in the existing technology in the field of two-dimensional facial expression recognition, but a large amount of unmarked expression image data cannot be used in practice. Supervised learning method for facial expression recognition, which can effectively improve the recognition rate of facial expressions when training data is insufficient

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
  • Semi-supervised learning facial expression recognition method based on fuzzy training samples
  • Semi-supervised learning facial expression recognition method based on fuzzy training samples
  • Semi-supervised learning facial expression recognition method based on fuzzy training samples

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0044] The present invention will be described in further detail below in conjunction with the accompanying drawings and specific embodiments.

[0045] like figure 1 Shown, a kind of semi-supervised learning human facial expression recognition method based on fuzzy training samples of the present invention, the method comprises the following steps:

[0046] (1) Face database data preprocessing specifically includes the following sub-steps:

[0047] (1.1) Face images are pre-classified by expression category: using the CK+ facial expression database of Carnegie Mellon University, select marked expression images, and put them according to the names of six types of expressions (happy, surprised, sad, angry, disgusted, and fearful). Under 6 folders;

[0048] (1.2) The image data is divided into a training set and a test set: the specific method is to select i pieces from the 6 types of expressions each time, a total of 6i samples as a labeled training set, and select j pieces fr...

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 semi-supervised learning facial expression recognition method based on fuzzy training samples. First, data in a face database is preprocessed; then, facial expressions are recognized using an improved SVM algorithm; and finally, unknown expression images are recognized. Under the condition that a same number of labeled samples are used, the expression recognition rate is improved by 3-7% by adding a large number of unlabeled samples. Under the condition that a few labeled samples are used, the recognition rate is improved using an STSVM algorithm to a level equivalent to the recognition rate of an SVM classifier obtained by using a large number of labeled samples.

Description

technical field [0001] The invention relates to the technical fields of image processing and pattern recognition, in particular to a semi-supervised learning self-training support vector machine classification method in the direction of two-dimensional facial expression recognition. Background technique [0002] Facial expression recognition generally includes three steps: facial image acquisition, feature extraction, and facial expression classification. When doing facial expression recognition classification, a certain sample may have both anger and sadness features. When performing classification, the performance of the classifier will be affected to a certain extent. At the same time, there are a large amount of fuzzy unlabeled data in real life, and traditional supervised learning cannot make good use of these data. The invention combines a semi-supervised learning algorithm and realizes more accurate classification of fuzzy samples by using a large amount of unmarked ...

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): G06K9/00G06K9/62
CPCG06V40/175G06F18/2155G06F18/2411
Inventor 胡浩基李娜雨蔡成飞刘佐珠
Owner ZHEJIANG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com