模式识别与人工智能
Wednesday, Apr. 2, 2025 Home      About Journal      Editorial Board      Instructions      Ethics Statement      Contact Us                   中文
  2021, Vol. 34 Issue (5): 423-433    DOI: 10.16451/j.cnki.issn1003-6059.202105005
Special Research on Detection, Discrimination and Tracking of Visual Object Current Issue| Next Issue| Archive| Adv Search |
Micro-Expression Recognition Algorithm Based on 3D Convolutional Neural Network and Optical Flow Fields from Neighboring Frames of Apex Frame
ZHANG Xuesen1, JIA Jingping1
1. School of Control and Computer Engineering, North China Elec-tric Power University, Beijing 102206

Download: PDF (1471 KB)   HTML (1 KB) 
Export: BibTeX | EndNote (RIS)      
Abstract  The existing micro-expression recognition technologies cannot make full use of the spatiotemporal features near the apex frame. Aiming at this problem, a micro-expression recognition algorithm based on 3D convolutional neural network and optical flow fields from the neighboring frames of the apex frame is proposed. Firstly, the optical flow fields between the adjacent frames before and after the apex frame are extracted. The important spatiotemporal information of micro-expressions are retained while the redundant information is removed and the computation load is reduced. Then, a 3D convolutional neural network is employed to extract the enhanced spatiotemporal features from the optical flow fields and thus the classification is completed. Finally, experiments on three spontaneous micro-expression databases show the proposed algorithm produces a better accuracy.
Key wordsMicro-Expression Recognition      3D Convolutional Neural Network      Optical Flow      Apex Frame     
Received: 09 October 2020     
ZTFLH: TP 391  
Fund:Beijing Natural Science Foundation(No.4162056),Fundamental Research Funds for the Central Universities(No.2016MS33)
Corresponding Authors: JIA Jingping, Ph.D., lecturer. His research interests include computer vision, machine learning and cybersecurity.   
About author:: ZHANG Xuesen, master student. His research interests include computer vision.
Service
E-mail this article
Add to my bookshelf
Add to citation manager
E-mail Alert
RSS
Articles by authors
ZHANG Xuesen
JIA Jingping
Cite this article:   
ZHANG Xuesen,JIA Jingping. Micro-Expression Recognition Algorithm Based on 3D Convolutional Neural Network and Optical Flow Fields from Neighboring Frames of Apex Frame[J]. , 2021, 34(5): 423-433.
URL:  
http://manu46.magtech.com.cn/Jweb_prai/EN/10.16451/j.cnki.issn1003-6059.202105005      OR     http://manu46.magtech.com.cn/Jweb_prai/EN/Y2021/V34/I5/423
Copyright © 2010 Editorial Office of Pattern Recognition and Artificial Intelligence
Address: No.350 Shushanhu Road, Hefei, Anhui Province, P.R. China Tel: 0551-65591176 Fax:0551-65591176 Email: bjb@iim.ac.cn
Supported by Beijing Magtech  Email:support@magtech.com.cn