Close

1. Identity statement
Reference TypeConference Paper (Conference Proceedings)
Sitesibgrapi.sid.inpe.br
Holder Codeibi 8JMKD3MGPEW34M/46T9EHH
Identifier8JMKD3MGPBW34M/3884JEB
Repositorysid.inpe.br/sibgrapi/2010/09.08.23.39
Last Update2010:09.08.23.39.01 (UTC) administrator
Metadata Repositorysid.inpe.br/sibgrapi/2010/09.08.23.39.01
Metadata Last Update2022:06.14.00.07.00 (UTC) administrator
DOI10.1109/SIBGRAPI.2010.12
Citation KeyQueirozCoMoBrJaMu:2010:GeFaGr
TitleGenerating Facial Ground Truth with Synthetic Faces
FormatPrinted, On-line.
Year2010
Access Date2024, Apr. 28
Number of Files1
Size5057 KiB
2. Context
Author1 Queiroz, Rossana B.
2 Cohen, Marcelo
3 Moreira, Juliano
4 Braun, Adriana
5 Jacques Junior, Julio C.
6 Musse, Soraia R.
Affiliation1 Pontifícia Universidade Católica do Rio Grande do Sul
2 Pontifícia Universidade Católica do Rio Grande do Sul
3 Pontifícia Universidade Católica do Rio Grande do Sul
4 Pontifícia Universidade Católica do Rio Grande do Sul
5 Pontifícia Universidade Católica do Rio Grande do Sul
6 Pontifícia Universidade Católica do Rio Grande do Sul
EditorBellon, Olga
Esperança, Claudio
e-Mail Addressfellowsheep@gmail.com
Conference NameConference on Graphics, Patterns and Images, 23 (SIBGRAPI)
Conference LocationGramado, RS, Brazil
Date30 Aug.-3 Sep. 2010
PublisherIEEE Computer Society
Publisher CityLos Alamitos
Book TitleProceedings
Tertiary TypeFull Paper
History (UTC)2010-10-01 04:19:39 :: fellowsheep@gmail.com -> administrator :: 2010
2022-06-14 00:07:00 :: administrator -> :: 2010
3. Content and structure
Is the master or a copy?is the master
Content Stagecompleted
Transferable1
Version Typefinaldraft
KeywordsComputer Vision
Ground Truth
Computer Animation
AbstractThis work describes a methodology for generation of facial ground truth with synthetic faces. Our focus is to provide a way to generate accurate data for the evaluation of Computer Vision algorithms, in terms of facial detection and its components. Such algorithms play a key role in face detection. We present a prototype in which we can generate facial animation videos using a 3D face models database, controlling face actions, illumination conditions and camera position. The facial animation platform allows us to generate animations with speech, facial expressions and eye motion, in order to approach realistic human face behavior. In addition, our model provides the ground truth of a set of facial feature points at each frame. As result, we are able to build a video database of synthetic human faces with ground truth, which can be used for training/evaluation of several algorithms for tracking and/or detection. We also present experiments using our generated videos to evaluate face, eye and mouth detection algorithms, comparing their performance with real video sequences.
Arrangement 1urlib.net > SDLA > Fonds > SIBGRAPI 2010 > Generating Facial Ground...
Arrangement 2urlib.net > SDLA > Fonds > Full Index > Generating Facial Ground...
doc Directory Contentaccess
source Directory Contentthere are no files
agreement Directory Contentthere are no files
4. Conditions of access and use
data URLhttp://urlib.net/ibi/8JMKD3MGPBW34M/3884JEB
zipped data URLhttp://urlib.net/zip/8JMKD3MGPBW34M/3884JEB
Languageen
Target FileCamera_Ready_70481.pdf
User Groupfellowsheep@gmail.com
Visibilityshown
5. Allied materials
Next Higher Units8JMKD3MGPEW34M/46SJT6B
8JMKD3MGPEW34M/4742MCS
Citing Item Listsid.inpe.br/sibgrapi/2022/05.14.20.21 3
Host Collectionsid.inpe.br/banon/2001/03.30.15.38
6. Notes
Empty Fieldsarchivingpolicy archivist area callnumber contenttype copyholder copyright creatorhistory descriptionlevel dissemination documentstage edition electronicmailaddress group isbn issn label lineage mark mirrorrepository nextedition notes numberofvolumes orcid organization pages parameterlist parentrepositories previousedition previouslowerunit progress project readergroup readpermission resumeid rightsholder schedulinginformation secondarydate secondarykey secondarymark secondarytype serieseditor session shorttitle sponsor subject tertiarymark type url volume


Close