Close
Metadata

1. Identity statement
Reference TypeConference Paper (Conference Proceedings)
Sitesibgrapi.sid.inpe.br
Holder Codeibi 8JMKD3MGPEW34M/46T9EHH
Identifier8JMKD3MGPAW/3M5KU35
Repositorysid.inpe.br/sibgrapi/2016/07.23.00.14
Last Update2016:07.23.14.51.58 (UTC) administrator
Metadata Repositorysid.inpe.br/sibgrapi/2016/07.23.00.14.14
Metadata Last Update2022:06.14.00.08.39 (UTC) administrator
DOI10.1109/SIBGRAPI.2016.021
Citation KeyOliveiraMeSoJúPeGo:2016:DaAuMe
TitleA Data Augmentation Methodology to Improve Age Estimation using Convolutional Neural Networks
FormatOn-line
Year2016
Access Date2024, May 01
Number of Files1
Size1374 KiB
2. Context
Author1 Oliveira, Ítalo de Pontes
2 Medeiros, João Lucas Peixoto
3 Sousa, Vinícius Fernandes de
4 Júnior, Adalberto Gomes Teixeira
5 Pereira, Eanes Torres
6 Gomes, Herman Martins
Affiliation1 UFCG
2 UFCG
3 UFCG
4 UFCG
5 UFCG
6 UFCG
EditorAliaga, Daniel G.
Davis, Larry S.
Farias, Ricardo C.
Fernandes, Leandro A. F.
Gibson, Stuart J.
Giraldi, Gilson A.
Gois, João Paulo
Maciel, Anderson
Menotti, David
Miranda, Paulo A. V.
Musse, Soraia
Namikawa, Laercio
Pamplona, Mauricio
Papa, João Paulo
Santos, Jefersson dos
Schwartz, William Robson
Thomaz, Carlos E.
e-Mail Addresshmg@computacao.ufcg.edu.br
Conference NameConference on Graphics, Patterns and Images, 29 (SIBGRAPI)
Conference LocationSão José dos Campos, SP, Brazil
Date4-7 Oct. 2016
PublisherIEEE Computer Society´s Conference Publishing Services
Publisher CityLos Alamitos
Book TitleProceedings
Tertiary TypeFull Paper
History (UTC)2016-07-23 14:51:59 :: hmg@computacao.ufcg.edu.br -> administrator :: 2016
2016-10-05 14:49:19 :: administrator -> hmg@computacao.ufcg.edu.br :: 2016
2016-10-13 10:50:38 :: hmg@computacao.ufcg.edu.br -> administrator :: 2016
2022-06-14 00:08:39 :: administrator -> :: 2016
3. Content and structure
Is the master or a copy?is the master
Content Stagecompleted
Transferable1
Version Typefinaldraft
Keywordsdata augmentation
age estimation
deep learning
fiducial points
face detection
AbstractRecent advances in deep learning methodologies are enabling the construction of more accurate classifiers. However, existing labeled face datasets are limited in size, which prevents CNN models from reaching their full generalization capabilities. A variety of techniques to generate new training samples based on data augmentation have been proposed, but the great majority is limited to very simple transformations. The approach proposed in this paper takes into account intrinsic information about human faces in order to generate an augmented dataset that is used to train a CNN, by creating photo-realistic smooth face variations based on Active Appearance Models optimized for human faces. An experimental evaluation taking CNN models trained with original and augmented versions of the MORPH face dataset allowed an increase of 10% in the F-Score and yielded Receiver Operating Characteristic curves that outperformed state-of-the-art work in the literature.
Arrangement 1urlib.net > SDLA > Fonds > SIBGRAPI 2016 > A Data Augmentation...
Arrangement 2urlib.net > SDLA > Fonds > Full Index > A Data Augmentation...
doc Directory Contentaccess
source Directory Content
PID4373767.pdf 22/07/2016 21:14 1.3 MiB
agreement Directory Content
agreement.html 22/07/2016 21:14 1.2 KiB 
4. Conditions of access and use
data URLhttp://urlib.net/ibi/8JMKD3MGPAW/3M5KU35
zipped data URLhttp://urlib.net/zip/8JMKD3MGPAW/3M5KU35
Languageen
Target FilePID4374341.pdf
User Grouphmg@computacao.ufcg.edu.br
Visibilityshown
Update Permissionnot transferred
5. Allied materials
Mirror Repositorysid.inpe.br/banon/2001/03.30.15.38.24
Next Higher Units8JMKD3MGPAW/3M2D4LP
8JMKD3MGPEW34M/4742MCS
Citing Item Listsid.inpe.br/sibgrapi/2016/07.02.23.50 5
Host Collectionsid.inpe.br/banon/2001/03.30.15.38
6. Notes
Empty Fieldsarchivingpolicy archivist area callnumber contenttype copyholder copyright creatorhistory descriptionlevel dissemination edition electronicmailaddress group isbn issn label lineage mark 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