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

A cross-dataset facial expression recognition model construction and recognition method

A facial expression and recognition model technology, applied in character and pattern recognition, acquisition/recognition of facial features, computer components, etc., can solve problems such as unsatisfactory clustering results

Active Publication Date: 2021-07-30
CHANGAN UNIV
View PDF2 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 provide a cross-dataset facial expression recognition model construction and recognition method to solve the problem of unsatisfactory clustering effect of cross-dataset expression recognition methods in the prior art

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 cross-dataset facial expression recognition model construction and recognition method
  • A cross-dataset facial expression recognition model construction and recognition method
  • A cross-dataset facial expression recognition model construction and recognition method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0031] The invention discloses a cross-dataset facial expression recognition model construction method, the method comprising:

[0032] Step 1, obtain facial expression image training set, described training set comprises the facial expression image of a plurality of pieces of marked facial expression in the first data set and the unmarked facial expression image of a plurality of pieces in the second data set, in described training set Each labeled facial expression image corresponds to a labeled label, and each unlabeled facial expression image corresponds to a random label;

[0033] In this embodiment, 327 facial expression images with marked expressions in the CK+ data set and 142 facial expression images with unmarked expressions in the JAFFE data set are respectively selected to form a training set of facial expression images, wherein the facial expression images in the CK+ data set are as follows: figure 2 As shown, the facial expression images in the JAFFE dataset are...

Embodiment 2

[0080] A cross-dataset facial expression recognition method, the facial expression recognition model described in the first embodiment recognizes the facial expression image to be recognized, and obtains the label of the facial expression image to be recognized.

[0081] In this example, for Figure 4 The facial expression image shown is recognized, and the recognition result is: 7-happy.

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 cross-dataset facial expression recognition model construction method and a recognition method. The reconstruction error of the training expression image is constrained by an adaptive non-negative weighting matrix, which strengthens the role of important features in image data representation and reduces the need for significant reconstruction. Useless features for errors. In addition, projecting the training set into an appropriate subspace through the mapping matrix can better reveal the intrinsic similarity between image samples across datasets, so that subspaces based on low-rank and sparse representations can learn robust image reconstructions. In order to facilitate the final cross-dataset facial expression recognition.

Description

technical field [0001] The invention relates to the field of facial expression recognition, in particular to a cross-data set facial expression recognition model construction and recognition method. Background technique [0002] Existing facial expression recognition methods are mainly based on the assumption that the captured test images and training images are from the same conditions and individuals, and these methods are limited by a large number of labeled samples. However, when the training and testing processes of these methods come from expression databases of different conditions and individuals, their recognition performance will drop significantly. At the same time, when the marked training samples are seriously insufficient, the existing facial expression recognition methods often have overfitting phenomenon in the learning process, so that the learned model cannot obtain the desired effect in the testing process. [0003] At present, only a few face recognition...

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): G06K9/00G06K9/62
CPCG06V40/174G06F18/23G06F18/2411G06F18/214
Inventor 马祥付俊妮
Owner CHANGAN 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