Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Micro expression automatic identification method based on multiple-dimensioned sampling

An automatic recognition and micro-expression technology, applied in character and pattern recognition, acquisition/recognition of facial features, instruments, etc., to achieve the effects of improving recognition rate, enhancing robustness, and enhancing description ability

Inactive Publication Date: 2016-11-09
SHANDONG UNIV
View PDF2 Cites 19 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although researchers have proposed some excellent feature descriptors in face recognition and macro-expression recognition, and achieved good results, in view of the spatio-temporal characteristics and computational complexity of micro-expressions, the above descriptors are directly extended to micro-expression recognition. is not feasible in

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 automatic identification method based on multiple-dimensioned sampling
  • Micro expression automatic identification method based on multiple-dimensioned sampling
  • Micro expression automatic identification method based on multiple-dimensioned sampling

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0040] An automatic micro-expression recognition method based on multi-scale sampling, such as figure 1 shown, including micro-expression image sequence preprocessing, micro-expression feature extraction and micro-expression recognition;

[0041] The micro-expression image sequence preprocessing includes face feature point detection, face alignment, and face sub-blocking in sequence; the face sub-blocking refers to dividing the first frame of the micro-expression image into sub-blocks according to the feature points;

[0042] The micro-expression feature extraction includes, in each sub-block, using the CPTOP (Cross Patterns on three orthogonal planes) operator to extract histogram feature vectors on the three planes of the gray-scaled expression sequence XY, XT and YT, and then cascading them into A high-dimensional feature vector is used as the feature vector of CPTOP; the high-dimensional feature vectors of the above-mentioned sub-blocks are cascaded into a higher-dimensio...

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 provides a micro expression automatic identification method based on multiple-dimensioned sampling. The method comprises micro expression image sequence preprocessing, micro expression feature extraction and micro expression identification. For the purpose of reducing influences exerted by face natural displacement and an ineffective area on micro expression identification, a method for automatically aligning a face and effectively partitioning a face area, and thus the robustness of an identification result is improved; and for the purpose of solving the defect of an existing feature descriptor, the invention brings forward a novel micro expression feature description operator CPTOP, the CPTOP operator the same sampling point number as a LBP-TOP operator yet employs a multiple-dimensioned sampling strategy, and under the same time complexity and space complexity, better description information is obtained.

Description

technical field [0001] The invention relates to an automatic micro-expression recognition method based on multi-scale sampling, belonging to the technical field of machine learning and pattern recognition. Background technique [0002] Human facial expression research originated in Darwin in the 19th century [1], and recently, Ekman and Erika [2] conducted a study of facial mapping behavior, verifying that microexpressions can provide a more comprehensive disclosure of hidden emotions. Micro-expression is a kind of fast expression. Although it lasts for a short time, it can reveal the true emotions of people’s heart, thus providing a reliable basis for judging people’s inner mental state [3]. Therefore, it is of great importance in judicial system and clinical diagnosis. Applications. Foreign research on micro-expressions started earlier, and they proposed and defined micro-expressions. They have made many achievements in assisting judicial organs in diagnosing cases, busin...

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): G06K9/00
CPCG06V40/174G06V40/172
Inventor 贲晛烨李传烨杨明强庞建华冯云聪任亿
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
Eureka Blog
Learn More
PatSnap group products