Expression Removal in 3D Faces for Recognition Purposes

We present an encoder-decoder neural network to remove deformations caused by expressions from 3D face images. It receives a 3D face with or without expressions as input and outputs its neutral form. Our objective is not to obtain the most realistic results but to enhance the accuracy of 3D face rec...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Proceedings (Brazilian Conference on Intelligent Systems. Online) s. 753 - 758
Hlavní autoři: Amparo Barbosa, Lucas, Dahia, Gabriel, Pamplona Segundo, Mauricio
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 01.10.2019
Témata:
ISSN:2643-6264
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract We present an encoder-decoder neural network to remove deformations caused by expressions from 3D face images. It receives a 3D face with or without expressions as input and outputs its neutral form. Our objective is not to obtain the most realistic results but to enhance the accuracy of 3D face recognition systems. To this end, we propose using a recognition-based loss function during training so that our network can learn to maintain important identity cues in the output. Our experiments using the Bosphorus 3D Face Database show that our approach successfully reduces the difference between face images from the same subject affected by different expressions and increases the gap between intraclass and interclass difference values. They also show that our synthetic neutral images improved the results of four different well-known face recognition methods.
AbstractList We present an encoder-decoder neural network to remove deformations caused by expressions from 3D face images. It receives a 3D face with or without expressions as input and outputs its neutral form. Our objective is not to obtain the most realistic results but to enhance the accuracy of 3D face recognition systems. To this end, we propose using a recognition-based loss function during training so that our network can learn to maintain important identity cues in the output. Our experiments using the Bosphorus 3D Face Database show that our approach successfully reduces the difference between face images from the same subject affected by different expressions and increases the gap between intraclass and interclass difference values. They also show that our synthetic neutral images improved the results of four different well-known face recognition methods.
Author Pamplona Segundo, Mauricio
Dahia, Gabriel
Amparo Barbosa, Lucas
Author_xml – sequence: 1
  givenname: Lucas
  surname: Amparo Barbosa
  fullname: Amparo Barbosa, Lucas
  organization: Federal University of Bahia, Brazil
– sequence: 2
  givenname: Gabriel
  surname: Dahia
  fullname: Dahia, Gabriel
  organization: Federal University of Bahia, Brazil
– sequence: 3
  givenname: Mauricio
  surname: Pamplona Segundo
  fullname: Pamplona Segundo, Mauricio
  organization: Federal University of Bahia, Brazil
BookMark eNotjNFKwzAUhqMoOGcfQLzpC7Tm5DRpcjnrpoOBMvV6JOmZRLamNFPc21vRm--Hj5_vkp11sSPGroGXANzc3q1nzfKlFBxMyTmgPGGZqTXUQkMlJMIpmwhVYaFGXrAspQ_OOQqOlZQTVs-_-4FSCrHL17SPX3aXhy7H-3xhPaV8G4fR-_jehcPv5_lz6GOidMXOt3aXKPvfKXtbzF-bx2L19LBsZqsiAOhD0YIUlUJr6xadVa0DZw0pSaS8JimIS4ekyTvA0QgC4St0XijhZKskTtnNXzcQ0aYfwt4Ox402Ao2s8Ac6m0jC
CODEN IEEPAD
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1109/BRACIS.2019.00135
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Xplore POP ALL
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP All) 1998-Present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Computer Science
EISBN 9781728142531
1728142539
EISSN 2643-6264
EndPage 758
ExternalDocumentID 8923954
Genre orig-research
GroupedDBID 6IE
6IF
6IL
6IN
AAJGR
AAWTH
ABLEC
ADZIZ
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
CHZPO
IEGSK
OCL
RIE
RIL
ID FETCH-LOGICAL-i118t-d152463aa7d3ba6db1ba9e65ee6c8e52e05b3e8ecb136c82e12c43bc262b5d653
IEDL.DBID RIE
IngestDate Wed Aug 27 02:49:49 EDT 2025
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i118t-d152463aa7d3ba6db1ba9e65ee6c8e52e05b3e8ecb136c82e12c43bc262b5d653
PageCount 6
ParticipantIDs ieee_primary_8923954
PublicationCentury 2000
PublicationDate 2019-Oct
PublicationDateYYYYMMDD 2019-10-01
PublicationDate_xml – month: 10
  year: 2019
  text: 2019-Oct
PublicationDecade 2010
PublicationTitle Proceedings (Brazilian Conference on Intelligent Systems. Online)
PublicationTitleAbbrev BRACIS
PublicationYear 2019
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0003203455
Score 1.7011195
Snippet We present an encoder-decoder neural network to remove deformations caused by expressions from 3D face images. It receives a 3D face with or without...
SourceID ieee
SourceType Publisher
StartPage 753
SubjectTerms 3D Images
Deep Learning
Face recognition
Facial Recognition
Image recognition
Neural networks
Strain
Three-dimensional displays
Training
Two dimensional displays
Title Expression Removal in 3D Faces for Recognition Purposes
URI https://ieeexplore.ieee.org/document/8923954
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LSwMxEB7a4sFT1VZ8k4NH1yabx2aPWlsUpJSq0FvZJLPQg7vSh_jzTbbb6sGLtzAEApOE-TL5Zj6Aa8k4Umtt5BQ1kUCXRx4cpRHThjOlLKN51V3_ORmN9HSajhtws6uFQcSKfIa3YVj95bvSrkOqrKc9GkmlaEIzSdSmVmuXT-Ex5ULK-uOS0bR3P7nrP70E9lbVkjIIuv0SUKnix7D9v5UPoPtTiEfGuxBzCA0sjqC9VWIg9cXsQDL4qgmtBZnge-mPD5kXhD-QYaBcEY9MyWRLFfJzxt695RKXXXgbDl77j1EtiRDN_UtgFTkfboXiWZY4bjLlDDNZikoiKqtRxkil4ajRGsa9JUYWW8GNjVVspFOSH0OrKAs8AaKVZDZzAo1wIlceJ-aO6twDLG10pvAUOsEPs49N14tZ7YKzv83nsB8cvaG5XUBrtVjjJezZz9V8ubiqtuobbNaVsw
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LTwIxEJ4gmugJFYxve_DoSrt90D0qQiAiIYgJN7JtZxMOLoaH8efbXRb04MVbM2nSZNpmvk6_mQ_gVjKO1FobOEVNINAlgQdHUcC04Uwpy2iSd9fvNfp9PR5HgxLcbWthEDEnn-F9Nsz_8t3MrrJUWV17NBJJsQO7UoiQrqu1thkVHlIupCy-LhmN6o_Dh2b3NeNv5U0pM0m3XxIqeQRpV_639iHUfkrxyGAbZI6ghOkxVDZaDKS4mlVotL4KSmtKhvg-8weITFPCn0g7I10Rj03JcEMW8nMG3sGzBS5q8NZujZqdoBBFCKb-LbAMnA-4QvE4bjhuYuUMM3GESiIqq1GGSKXhqNEaxr0lRBZawY0NVWikU5KfQDmdpXgKRCvJbOwEGuFEojxSTBzViYdY2uhY4RlUMz9MPtZ9LyaFC87_Nt_Afmf00pv0uv3nCzjInL4mvV1CeTlf4RXs2c_ldDG_zrftG2djmPo
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%3Abook&rft.genre=proceeding&rft.title=Proceedings+%28Brazilian+Conference+on+Intelligent+Systems.+Online%29&rft.atitle=Expression+Removal+in+3D+Faces+for+Recognition+Purposes&rft.au=Amparo+Barbosa%2C+Lucas&rft.au=Dahia%2C+Gabriel&rft.au=Pamplona+Segundo%2C+Mauricio&rft.date=2019-10-01&rft.pub=IEEE&rft.eissn=2643-6264&rft.spage=753&rft.epage=758&rft_id=info:doi/10.1109%2FBRACIS.2019.00135&rft.externalDocID=8923954