Research on Reconstruction Method of Occluded Micro-Expressions Based on Quantized Denoising Autoencoder

Micro-expressions serve as a crucial basis for psychological health diagnoses, and occlusions caused by objects, such as glasses or masks, can make micro-expression recognition challenging. Existing reconstruction methods for occluded micro-expressions rely primarily on reconstructing RGB texture in...

Full description

Saved in:
Bibliographic Details
Published in:Ji suan ji gong cheng Vol. 51; no. 5; pp. 288 - 304
Main Author: LIU Hui, GUO Te, LIU Dong, LI Yingying
Format: Journal Article
Language:Chinese
English
Published: Editorial Office of Computer Engineering 15.05.2025
Subjects:
occluded micro-expression recognition|feature reconstruction|optical flow|dynamic image|denoising autoencoder
ISSN:1000-3428
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract Micro-expressions serve as a crucial basis for psychological health diagnoses, and occlusions caused by objects, such as glasses or masks, can make micro-expression recognition challenging. Existing reconstruction methods for occluded micro-expressions rely primarily on reconstructing RGB texture information, which leads to issues such as information redundancy and difficulties in achieving precise texture reconstruction. In addition, the models used in such reconstruction methods often involve symmetric autoencoders based on U-Net and Generative Adversarial Networks (GAN); However, the former suffers from limited reconstruction capabilities in shallow symmetric structures, and the latter faces challenges in terms of adversarial loss convergence speed. This paper proposes a method for reconstructing dynamic flow features in occluded regions of micro-expressions based on a vector-quantized denoising autoencoder. First, dynamic flow, a robust feature representation resilient to lighting variations, is proposed based on optical flow and dynamic images, effectively aggregating motion information from all TVL1 optical flows and simplifying the texture information. Then, a two-pair Vector Quantized Denoising Autoencoder (VQ-DAE) based on the discrete encoding Vector Quantized Variational Autoencoder (VQ-VAE) is introduced to reconstruct dynamic flow features in occluded regions of micro-expressions to facilitate the recognition of occluded micro-expressions. Experimental results demonstrate that this approach effectively reconstructs motion information in occluded regions, achieving accuracy rates of 77.89%, 72.02%, and 61.04% on the CASME, CAS(ME)2, and CASME Ⅱ datasets, respectively. Compared to traditional, spatial-attention-, and self-attention-based methods, our method leads to significant improvements in accuracy, Unweighted Average Recall (UAR), and Macro-F1.
AbstractList Micro-expressions serve as a crucial basis for psychological health diagnoses, and occlusions caused by objects, such as glasses or masks, can make micro-expression recognition challenging. Existing reconstruction methods for occluded micro-expressions rely primarily on reconstructing RGB texture information, which leads to issues such as information redundancy and difficulties in achieving precise texture reconstruction. In addition, the models used in such reconstruction methods often involve symmetric autoencoders based on U-Net and Generative Adversarial Networks (GAN); However, the former suffers from limited reconstruction capabilities in shallow symmetric structures, and the latter faces challenges in terms of adversarial loss convergence speed. This paper proposes a method for reconstructing dynamic flow features in occluded regions of micro-expressions based on a vector-quantized denoising autoencoder. First, dynamic flow, a robust feature representation resilient to lighting variations, is proposed based on optical flow and dynamic images, effectively aggregating motion information from all TVL1 optical flows and simplifying the texture information. Then, a two-pair Vector Quantized Denoising Autoencoder (VQ-DAE) based on the discrete encoding Vector Quantized Variational Autoencoder (VQ-VAE) is introduced to reconstruct dynamic flow features in occluded regions of micro-expressions to facilitate the recognition of occluded micro-expressions. Experimental results demonstrate that this approach effectively reconstructs motion information in occluded regions, achieving accuracy rates of 77.89%, 72.02%, and 61.04% on the CASME, CAS(ME)2, and CASME Ⅱ datasets, respectively. Compared to traditional, spatial-attention-, and self-attention-based methods, our method leads to significant improvements in accuracy, Unweighted Average Recall (UAR), and Macro-F1.
Author LIU Hui, GUO Te, LIU Dong, LI Yingying
Author_xml – sequence: 1
  fullname: LIU Hui, GUO Te, LIU Dong, LI Yingying
  organization: 1. College of Computer and Information Engineering, Henan Normal University, Xinxiang 453007, Henan, China;2. Engineering Technology Research Center for Computing Intelligence and Data Mining of Henan Colleges, Xinxiang 453007, Henan, China;3. School of Cybersecurity, Strategic Support Force Information Engineering University, Zhengzhou 450002, Henan, China
BookMark eNo9jF1LwzAYRnMxwU39D_UHtOarbXI559TBxnDsvqRv3m4ZMxlJC-qvt6h49XAOh2dGJj54JOSe0YLpqlYPp8Kl5AtGKc2F5KqgtFJa6gmZ_rtrMkvpRKnknNIpOe4woYlwzILPdgjBpz4O0LsRN9gfg81Cl20BzoNFm20cxJAvPy4RUxqblD2aNPqxfhuM793XCE_og0vOH7L50Af0ECzGW3LVmXPCu7-9Ifvn5X7xmq-3L6vFfJ1bJlSfYyUF8k5rXQqpKbRCqY63QhghWMlqqbgqrWxbNMxWzOga-NiZ1iID0Yobsvq9tcGcmkt07yZ-NsG45keEeGhM7B2csaksmAqgK5ExqXmtW9VZaWttFbNgK_ENtNhp-w
ContentType Journal Article
DBID DOA
DOI 10.19678/j.issn.1000-3428.0068949
DatabaseName DOAJ Directory of Open Access Journals
DatabaseTitleList
Database_xml – sequence: 1
  dbid: DOA
  name: Directory of Open Access Journals
  url: https://www.doaj.org/
  sourceTypes: Open Website
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EndPage 304
ExternalDocumentID oai_doaj_org_article_6dca6ccf5e1149279b8fd4d79d81dcd6
GroupedDBID -0Y
5XA
5XJ
92H
92I
ABJNI
ACGFS
ADMLS
ALMA_UNASSIGNED_HOLDINGS
CCEZO
CUBFJ
CW9
GROUPED_DOAJ
TCJ
TGT
U1G
U5S
ID FETCH-LOGICAL-d138t-e643e2f99953490cb388f2b33a33151748285d4bbea1d61a97c2490abde1c3b3
IEDL.DBID DOA
ISSN 1000-3428
IngestDate Mon Nov 03 22:01:13 EST 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 5
Language Chinese
English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-d138t-e643e2f99953490cb388f2b33a33151748285d4bbea1d61a97c2490abde1c3b3
OpenAccessLink https://doaj.org/article/6dca6ccf5e1149279b8fd4d79d81dcd6
PageCount 17
ParticipantIDs doaj_primary_oai_doaj_org_article_6dca6ccf5e1149279b8fd4d79d81dcd6
PublicationCentury 2000
PublicationDate 2025-05-15
PublicationDateYYYYMMDD 2025-05-15
PublicationDate_xml – month: 05
  year: 2025
  text: 2025-05-15
  day: 15
PublicationDecade 2020
PublicationTitle Ji suan ji gong cheng
PublicationYear 2025
Publisher Editorial Office of Computer Engineering
Publisher_xml – name: Editorial Office of Computer Engineering
SSID ssj0042200
Score 2.291255
Snippet Micro-expressions serve as a crucial basis for psychological health diagnoses, and occlusions caused by objects, such as glasses or masks, can make...
SourceID doaj
SourceType Open Website
StartPage 288
SubjectTerms occluded micro-expression recognition|feature reconstruction|optical flow|dynamic image|denoising autoencoder
Title Research on Reconstruction Method of Occluded Micro-Expressions Based on Quantized Denoising Autoencoder
URI https://doaj.org/article/6dca6ccf5e1149279b8fd4d79d81dcd6
Volume 51
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVAON
  databaseName: Directory of Open Access Journals
  issn: 1000-3428
  databaseCode: DOA
  dateStart: 20160101
  customDbUrl:
  isFulltext: true
  dateEnd: 99991231
  titleUrlDefault: https://www.doaj.org/
  omitProxy: false
  ssIdentifier: ssj0042200
  providerName: Directory of Open Access Journals
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrZ1LS8NAEMcXERE9iE98s4LX2Gx2k-weW23xYKtCD72V7AsrkkgfIn56Zzap9ubFSyAJCWEmmf3PZvY3hFwr5rTIDYtMJnkkVKyjIhWwkXFunC6Ez8JC4Yd8MJCjkXpaafWFNWE1Hrg2XCuzpsiM8akD5a6SXGnprbC5sqC0jA2wbVA9y2SqjsEiSeKaQxBDlAGFvUmuwso8CM2t1_B53fycw9IuqRCmuULtD8NLb5fsNLqQtuvn2SNrrtwn2yu0wAPysqySo1VJMW38hb_SfmgETStPH415W1hnaR9L7aLuZ1PpWs5oB0Ysixc_L8Ceky_YuXNlNcHpAtpezCuEWlo3PSTDXnd4ex81jRIiy7icRw5khUs8aL2Ug7mN5lL6RHNecM4QRY2YOiu0dgWzGStUbiDrigttHTNc8yOyXlalOyY0TjyobRa7VHr8hSu1THPhjPdMay_lCemgjcbvNQpjjHDqcABcNm5cNv7LZaf_cZMzspVgK14EqabnZB0M7i7IhvmYT2bTy_A2fAPKkrto
linkProvider Directory of Open Access Journals
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Research+on+Reconstruction+Method+of+Occluded+Micro-Expressions+Based+on+Quantized+Denoising+Autoencoder&rft.jtitle=Ji+suan+ji+gong+cheng&rft.au=LIU+Hui%2C+GUO+Te%2C+LIU+Dong%2C+LI+Yingying&rft.date=2025-05-15&rft.pub=Editorial+Office+of+Computer+Engineering&rft.issn=1000-3428&rft.volume=51&rft.issue=5&rft.spage=288&rft.epage=304&rft_id=info:doi/10.19678%2Fj.issn.1000-3428.0068949&rft.externalDBID=DOA&rft.externalDocID=oai_doaj_org_article_6dca6ccf5e1149279b8fd4d79d81dcd6
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1000-3428&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1000-3428&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1000-3428&client=summon