PSYCH OpenIR  > 脑与认知科学国家重点实验室
A Main Directional Mean Optical Flow Feature for Spontaneous Micro-Expression Recognition
Liu, Yong-Jin1; Zhang, Jin-Kai1; Yan, Wen-Jing3; Wang, Su-Jing2; Zhao, Guoying4,5; Fu, Xiaolan2
Source PublicationIEEE Transactions on Affective Computing

Micro-expressions are brief facial movements characterized by short duration, involuntariness and low intensity. Recognition of spontaneous facial micro-expressions is a great challenge. In this paper, we propose a simple yet effective Main Directional Mean Optical-flow (MDMO) feature for micro-expression recognition. We apply a robust optical flow method on micro-expression video clips and partition the facial area into regions of interest (ROIs) based partially on action units. The MDMO is a ROI-based, normalized statistic feature that considers both local statistic motion information and its spatial location. One of the significant characteristics of MDMO is that its feature dimension is small. The length of a MDMO feature vector is 36 x 2 = 72, where 36 is the number of ROIs. Furthermore, to reduce the influence of noise due to head movements, we propose an optical-flow-driven method to align all frames of a micro-expression video clip. Finally, a SVM classifier with the proposed MDMO feature is adopted for micro-expression recognition. Experimental results on three spontaneous micro-expression databases, namely SMIC, CASME and CASME II, show that the MDMO can achieve better performance than two state-of-the-art baseline features, i.e., LBP-TOP and HOOF.

KeywordMicro-expression optical flow recognition feature
Indexed BySCI
Funding OrganizationNational Natural Science Foundation of China(61322206 ; Beijing Natural Science Foundation(4152055) ; Open Projects Program of National Laboratory of Pattern Recognition(201306295) ; TNList Cross-discipline Foundation ; Academy of Finland ; Infotech Oulu ; 61521002 ; 61379095 ; 61375009)
WOS Research AreaComputer Science
WOS SubjectComputer Science, Artificial Intelligence ; Computer Science, Cybernetics
WOS IDWOS:000389328800001
WOS HeadingsScience & Technology ; Technology
Citation statistics
Cited Times:30[WOS]   [WOS Record]     [Related Records in WOS]
Document Type期刊论文
Affiliation1.Tsinghua Univ, Dept Comp Sci & Technol, Tsinghua Natl Lab Informat Sci & Technol, Beijing, Peoples R China
2.Chinese Acad Sci, Inst Psychol, State Key Lab Brain & Cognit Sci, Beijing 100101, Peoples R China
3.Wenzhou Univ, Coll Teacher Educ, Wenzhou 325035, Peoples R China
4.Univ Oulu, Ctr Machine Vis Res, Infotech Oulu, POB 4500, FI-90014 Oulu, Finland
5.Univ Oulu, Dept Elect & Informat Engn, POB 4500, FI-90014 Oulu, Finland
Recommended Citation
GB/T 7714
Liu, Yong-Jin,Zhang, Jin-Kai,Yan, Wen-Jing,et al. A Main Directional Mean Optical Flow Feature for Spontaneous Micro-Expression Recognition[J]. IEEE Transactions on Affective Computing,2016,7(4):299-310.
APA Liu, Yong-Jin,Zhang, Jin-Kai,Yan, Wen-Jing,Wang, Su-Jing,Zhao, Guoying,&Fu, Xiaolan.(2016).A Main Directional Mean Optical Flow Feature for Spontaneous Micro-Expression Recognition.IEEE Transactions on Affective Computing,7(4),299-310.
MLA Liu, Yong-Jin,et al."A Main Directional Mean Optical Flow Feature for Spontaneous Micro-Expression Recognition".IEEE Transactions on Affective Computing 7.4(2016):299-310.
Files in This Item:
File Name/Size DocType Version Access License
A Main Directional M(762KB)期刊论文出版稿限制开放CC BY-NC-SAView Application Full Text
Related Services
Recommend this item
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Liu, Yong-Jin]'s Articles
[Zhang, Jin-Kai]'s Articles
[Yan, Wen-Jing]'s Articles
Baidu academic
Similar articles in Baidu academic
[Liu, Yong-Jin]'s Articles
[Zhang, Jin-Kai]'s Articles
[Yan, Wen-Jing]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Liu, Yong-Jin]'s Articles
[Zhang, Jin-Kai]'s Articles
[Yan, Wen-Jing]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: A Main Directional Mean Optical Flow Feature for Spontaneous Micro Expression Recognition.pdf
Format: Adobe PDF
All comments (0)
No comment.

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