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

A micro-expression recognition method based on macro-expression knowledge transfer

A recognition method and micro-expression technology, applied in the field of pattern recognition and machine learning, can solve problems such as difficulty in model training, low micro-expression recognition rate, and insufficient micro-expression samples

Active Publication Date: 2019-03-29
SHANDONG UNIV
View PDF4 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, due to the lack of marked micro-expression samples in the current micro-expression database, there are too few samples that can be used for model training, which has caused certain difficulties in the training of the model, making it impossible to train a model with high performance for micro-expression recognition, which leads to the problem of low micro-expression recognition rate

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 micro-expression recognition method based on macro-expression knowledge transfer
  • A micro-expression recognition method based on macro-expression knowledge transfer
  • A micro-expression recognition method based on macro-expression knowledge transfer

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0063] A micro-expression recognition method based on macro-expression knowledge transfer, such as figure 1 shown, including the following steps:

[0064] (1) Divide facial expressions and micro-expressions into blocks: according to the facial motion coding system proposed by Professor Ekman, select 27 pixel points related to facial expression and micro-expression recognition, and take these 27 pixel points as the center Take the block and get 27 blocks. Using multi-task learning, these blocks are respectively subjected to subsequent model training, thereby reducing the interference of other information on the face to the training. Figure 4 (a) is a schematic diagram of macro-expression in 27 points related to macro-expression and micro-expression recognition; Figure 4 (b) is a schematic diagram of micro-expression in 27 points related to macro-expression and micro-expression recognition;

[0065] (2) Perform feature extraction on expressions and micro-expressions, extract L...

Embodiment 2

[0141] According to a kind of micro-expression recognition method based on macro-expression knowledge migration described in embodiment 1, its difference is:

[0142] Given a gallery sample set X, block the samples;

[0143] Extract sample features to get Indicates the t-th block of the j-th sample of the i-th class in the X sample set;

[0144] The obtained projection T represents the total number of blocks, according to the category of the sample and the number of blocks multiplied by the corresponding projection matrix, to obtain the characteristics in the public space, that is

[0145] For any probe sample y, still extract features according to the above method, get {y t |t=1,...,T}, since the category of this sample is unknown, one problem we face is how to choose the projection matrix pass After projection, c common subspaces are obtained. These c common subspaces are parallel, but because the approach and distance criteria of the samples are different, so we ...

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

PropertyMeasurementUnit
Frame rateaaaaaaaaaa
Login to View More

Abstract

The invention relates to a micro-expression recognition method based on macro-expression knowledge transfer, comprising the following steps: (1) partitioning the expression and the micro-expression; (2) performing feature extraction of facial expression and microexpression, performing LBP feature extraction and optical flow feature extraction; (3) constructing a micro-expression recognition modelof macro-expression knowledge transfer, that is, mapping a specific class of expression and micro-expression learning, and projecting the expression and micro-expression onto multiple common discriminant subspaces; (4) classifying and recognizing the microexpression by a nearest neighbor classifier based on Euclidean distance. On the one hand, multi-feature learning can combine the characteristicsof different features to achieve the best recognition results. On the other hand, multi-task learning is to take the feature points as the center to reduce the influence of other irrelevant regions of the face on the experimental results. Feature points here mainly refer to the key points related to facial expression and micro-expression recognition.

Description

technical field [0001] The invention relates to a micro-expression recognition method based on macro-expression knowledge transfer, and belongs to the technical field of pattern recognition and machine learning. Background technique [0002] Micro-expressions are the external manifestations of human psychological behavior, which can reveal the true emotions that people want to hide. Micro-expressions were first discovered by Haggard and Isaacs, and have the characteristics of low intensity and short duration. The duration of micro-expression is generally less than 1 / 5 second, and it is fleeting. Usually, the person making the expression and the observer cannot perceive the existence of micro-expression, and it is not controlled by people, and can reflect the true thoughts of people. Therefore, an important application of micro-expressions in real life is polygraph detection, which has important applications in national security, judicial trials, and prison management. [0...

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
IPC IPC(8): G06K9/00
CPCG06V40/168G06V40/174
Inventor 贲晛烨朱雪娜周斌肖瑞雪王保键黄以正
Owner SHANDONG 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