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

Filter design based light flow vector micro-expression generation phase detecting method

A technology of filter design and detection method, which is applied in the direction of instruments, calculations, computer components, etc., can solve the problem that the positioning mode cannot be unified in the micro-expression stage, and achieve the effect of simple and clear operation, easy operation, and error elimination

Inactive Publication Date: 2018-04-13
SOUTHEAST UNIV
View PDF7 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The technical problem to be solved by the present invention is to provide an optical flow vector micro-expression generation stage detection method based on filter design, which can solve the problem that the positioning mode of the micro-expression generation stage cannot be unified

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
  • Filter design based light flow vector micro-expression generation phase detecting method
  • Filter design based light flow vector micro-expression generation phase detecting method
  • Filter design based light flow vector micro-expression generation phase detecting method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0023] Such as figure 1 As shown, an optical flow vector micro-expression generation stage detection method based on filter design includes the following steps:

[0024] (1) Centering and normalization of optical flow motion features; firstly, the key points of the face in the first frame of the sequence are located, and other key points of the face in the video sequence are updated by the optical flow method to achieve the purpose of tracking. Small regions of interest (ROIs) are established around facial key points, and the average optical flow of these areas is used as the motion feature of the current frame. The purpose of ROIs is to balance the inaccuracy of the key point detection algorithm. The optical flow vectors around each key point can be grouped with the FACS system, so that active micro-expression motor units (AU) can be detected, and these active motor units are consistent with the largest motion amplitude, which is spatial synthesis, and then by The vectors ar...

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 filter design based light flow vector micro-expression generation phase detecting method. The method includes steps of (1) performing decentralization and normalization on light flow motion features; (2) adopting a signal attenuation method for positioning; (3) performing micro-expression automatic detection and identification. The invention has beneficial effects that human face key point areas relating to muscle motion when the micro-expressions generate can be adopted in a targeted manner such that effective motion features can be extracted effectively and redundant information unrelated to micro-expression generation can be eliminated; decentralization and normalization are performed on the light flow motion features such that influence caused by distance between a photographing object and a lens and different human face shapes can be weakened effectively and errors caused by head integral motion can be eliminated; start frame and end frame positioning ofindicators are designed referring to a filter and a uniform standard is set for micro-expression detection and can be applied to different databases; a detection system can visualize the whole detection process practically and simple and easy operation is achieved.

Description

technical field [0001] The invention relates to the technical field of micro-expression detection methods, in particular to an optical flow vector micro-expression generation stage detection method based on filter design. Background technique [0002] Microexpressions can be used in sentiment analysis because they reveal an individual's true emotions. But unlike facial expressions, microexpressions are weak, transient, unsystematic, and only appear in localized areas of the face, so microexpression analysis is more challenging than expression analysis. In computer vision, most microexpression-related work focuses on recognition, such as identifying labeled segmented video segments containing microexpressions from the start frame to the end frame. However, the premise of automatic recognition of micro-expressions is that the machine can automatically locate the occurrence stage of micro-expressions, so as to carry out the next step of recognition. In real-life scenarios, it...

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): G06K9/00G06T7/269
CPCG06T7/269G06T2207/10016G06T2207/30201G06V40/176
Inventor 郑文明李超龙李强
Owner SOUTHEAST 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