Micro expression recognition method based on multi-feature multi-task dictionary sparse migration learning

A transfer learning and recognition method technology, applied in the field of modal recognition and machine learning, can solve the problems of incomplete sample label information, small number of micro-expression databases, unsatisfactory results, etc., and achieve the effect of improving recognition performance

Active Publication Date: 2018-10-12
SHANDONG UNIV
View PDF9 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] At present, all kinds of micro-expression databases have the problem of small number and incomplete sample label information, so it is difficult to train an effective model. Considering that the traditional facial expression database has a large number of samples, the human face macro-expression and Establishing connections with micro-expressions and rea

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
  • Micro expression recognition method based on multi-feature multi-task dictionary sparse migration learning
  • Micro expression recognition method based on multi-feature multi-task dictionary sparse migration learning
  • Micro expression recognition method based on multi-feature multi-task dictionary sparse migration learning

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0066] Example 1

[0067] A micro-expression recognition method based on sparse migration learning of multi-feature and multi-task macro expression dictionary, such as figure 1 Shown, including training phase, testing phase;

[0068] A. The training phase includes the following steps:

[0069] (1) Divide each picture in the micro-expression domain into several blocks; examples of sample pictures in the macro-expression domain are as figure 2 As shown; examples of sample pictures in the micro expression domain are as image 3 Shown

[0070] (2) Extract the most representative features of the macro expression domain and the micro expression domain; for the macro expression domain, the most representative feature extracted is the LBP feature; the LBP feature is the most representative texture feature of the macro expression domain; In order to fully reflect the characteristics of the dynamic sequence of micro-expression, for each segment in the micro-expression domain, the most represe...

Example Embodiment

[0079] Example 2

[0080] According to the micro-expression recognition method based on the sparse migration learning of the multi-feature multi-task macro-expression dictionary described in Embodiment 1, the difference is that:

[0081] The step (2), extracting the most representative features from the macro expression domain and the micro expression domain, includes:

[0082] a. Perform feature extraction on the macro expression domain and the micro expression domain. For the macro expression domain, the extracted features n x Refers to the number of samples in the macro expression domain; Refers to n in the macro expression domain x LBP features extracted from samples, R refers to the size of matrix X; m x Refers to the feature dimension of the macro expression domain;

[0083] For the micro-expression domain, since the micro-expression has extracted four different sets of features, the extracted features n y Refers to the number of samples in the micro expression domain;

[0084]...

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 a micro expression recognition method based on multi-feature multi-task dictionary sparse migration learning. The micro expression recognition method comprises a training phase and a test phase. According to the micro expression recognition method provided by the invention, a macro expression and a micro expression are projected into a public space by means of projection,and in order to simplify the calculation and to improve the efficiency, sparse dictionary representation is performed on the projected data; in order to further reduce the data difference between thetwo domains, dictionaries of the two domains are reconstructed from each other to realize the relevance of the dictionaries, so that projected sparse representation matrixes generate greater correlation; in order to fully express the characteristics of the micro expression, in the micro expression recognition method provided by the invention, four kinds of different features are extracted for themicro expression, and the optimal combination is achieved by the selection of multiple features; and in order to highlight the detailed expression of the micro expression, the multi-task idea is imported by the micro expression recognition method provided by the invention to further enhance the recognition effect.

Description

technical field [0001] The invention relates to a micro-expression recognition method based on multi-feature multi-task dictionary sparse transfer learning, and belongs to the technical field of modal recognition and machine learning. Background technique [0002] Microexpressions are extremely short-lived, involuntary facial expressions that people reveal when they are suppressed or trying to hide their true emotions. This subtle expression was first discovered by Haggard and Issacs in 1966. Facial expressions in the traditional sense (we call them macro expressions) are more decorative. A normal adult can show his satisfactory expression after brain thinking, while micro-expression is inadvertently The expression revealed is the most real emotional leakage of a person, so it is difficult to pass the "screening" of the brain, so micro-expressions are more likely to reveal a person's real inner activities. Due to the characteristics of micro-expressions, it is considered a ...

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
CPCG06V40/174G06V40/168G06V40/172
Inventor 贲晛烨冯云聪韩民朱雪娜张鑫陈瑞敏
Owner SHANDONG UNIV
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