PSYCH OpenIR  > 中国科学院心理健康重点实验室
Hierarchical support vector machine for facial micro-expression recognition
Pan, Hang1; Xie, Lun1; Lv, Zeping2; Li, Juan3; Wang, Zhiliang1
First AuthorPan, Hang
Correspondent Email(lun xie) xielun@ustb.edu.cn
Contribution Rank3
Abstract

The sample category distribution of spontaneous facial micro-expression datasets is unbalanced, due to the experimental environment, collection equipment, and individualization of subjects, which brings great challenges to micro-expression recognition. Therefore, this paper introduces a micro-expression recognition model based on the Hierarchical Support Vector Machine (H-SVM) to reduce the interference of sample category distribution imbalance. First, we calculated the position of the apex frame in the micro-expression image sequence. To keep micro-expression frames balanced, we sparsely sample the images sequence according to the apex frame. Then, the Low-level Descriptors of the region of interest of the micro-expression image sequence and the High-level Descriptors of apex frame are extracted. Finally, the H-SVM model is used to classify the fusion features of different levels. The experimental results on SMIC, CAMSE2, SAMM, and their composite datasets show that our method can achieve superior performance in micro-expression recognition.

KeywordMicro-expression recognition Sample imbalance Features fusion Hierarchical support vector machine
2020-08-21
Language英语
DOI10.1007/s11042-020-09475-4
Source PublicationMULTIMEDIA TOOLS AND APPLICATIONS
ISSN1380-7501
Pages31451–31465
Subtypearticle
Indexed BySCI
Funding ProjectNational Key R&D Program of China[2018YFC 2001700] ; National Natural Science Foundation of China[61672093] ; Beijing Municipal Natural Science Foundation[L192005] ; Advanced Innovation Center for Intelligent Robots and Systems Open Research Project[2018IRS01]
PublisherSPRINGER
WOS KeywordBINARY PATTERNS ; CLASSIFICATION
WOS Research AreaComputer Science ; Engineering
WOS SubjectComputer Science, Information Systems ; Computer Science, Software Engineering ; Computer Science, Theory & Methods ; Engineering, Electrical & Electronic
WOS IDWOS:000561259300001
Funding OrganizationNational Key R&D Program of China ; National Natural Science Foundation of China ; Beijing Municipal Natural Science Foundation ; Advanced Innovation Center for Intelligent Robots and Systems Open Research Project
Citation statistics
Cited Times:4[WOS]   [WOS Record]     [Related Records in WOS]
Document Type期刊论文
Identifierhttp://ir.psych.ac.cn/handle/311026/32493
Collection中国科学院心理健康重点实验室
Corresponding AuthorXie, Lun
Affiliation1.Univ Sci & Technol Beijing, Sch Comp & Commun Engn, Beijing, Peoples R China
2.Natl Res Ctr Rehabil Tech Aids, Affiliated Rehabil Hosp, Beijing, Peoples R China
3.Chinese Acad Sci, Ctr Aging Psychol, Inst Psychol, Key Lab Mental Hlth, Beijing, Peoples R China
Recommended Citation
GB/T 7714
Pan, Hang,Xie, Lun,Lv, Zeping,et al. Hierarchical support vector machine for facial micro-expression recognition[J]. MULTIMEDIA TOOLS AND APPLICATIONS,2020:31451–31465.
APA Pan, Hang,Xie, Lun,Lv, Zeping,Li, Juan,&Wang, Zhiliang.(2020).Hierarchical support vector machine for facial micro-expression recognition.MULTIMEDIA TOOLS AND APPLICATIONS,31451–31465.
MLA Pan, Hang,et al."Hierarchical support vector machine for facial micro-expression recognition".MULTIMEDIA TOOLS AND APPLICATIONS (2020):31451–31465.
Files in This Item:
File Name/Size DocType Version Access License
Hierarchical support(1277KB)期刊论文出版稿限制开放CC BY-NC-SAApplication Full Text
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Pan, Hang]'s Articles
[Xie, Lun]'s Articles
[Lv, Zeping]'s Articles
Baidu academic
Similar articles in Baidu academic
[Pan, Hang]'s Articles
[Xie, Lun]'s Articles
[Lv, Zeping]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Pan, Hang]'s Articles
[Xie, Lun]'s Articles
[Lv, Zeping]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.