Close
Metadata

1. Identity statement
Reference TypeConference Paper (Conference Proceedings)
Sitesibgrapi.sid.inpe.br
Holder Codeibi 8JMKD3MGPEW34M/46T9EHH
Identifier8JMKD3MGPEW34M/3U2JUJH
Repositorysid.inpe.br/sibgrapi/2019/09.09.20.40
Last Update2019:09.09.20.40.51 (UTC) administrator
Metadata Repositorysid.inpe.br/sibgrapi/2019/09.09.20.40.51
Metadata Last Update2022:06.14.00.09.33 (UTC) administrator
DOI10.1109/SIBGRAPI.2019.00034
Citation KeyAbelloJr:2019:OpSuRe
TitleOptimizing Super Resolution for Face Recognition
FormatOn-line
Year2019
Access Date2024, Oct. 15
Number of Files1
Size977 KiB
2. Context
Author1 Abello, Antonio Augusto
2 Jr, Roberto Hirata
Affiliation1 University of São Paulo, Brazil
2 University of São Paulo, Brazil
EditorOliveira, Luciano Rebouças de
Sarder, Pinaki
Lage, Marcos
Sadlo, Filip
e-Mail Addressabello@ime.usp.br
Conference NameConference on Graphics, Patterns and Images, 32 (SIBGRAPI)
Conference LocationRio de Janeiro, RJ, Brazil
Date28-31 Oct. 2019
PublisherIEEE Computer Society
Publisher CityLos Alamitos
Book TitleProceedings
Tertiary TypeFull Paper
History (UTC)2019-09-09 20:40:51 :: abello@ime.usp.br -> administrator ::
2022-06-14 00:09:33 :: administrator -> abello@ime.usp.br :: 2019
3. Content and structure
Is the master or a copy?is the master
Content Stagecompleted
Transferable1
Version Typefinaldraft
Keywordsdeep learning
super-resolution
face-recognition
AbstractFace Super-Resolution is a subset of Super Resolution (SR) that aims to retrieve a high-resolution (HR) image of a face from a lower resolution input. Recently, Deep Learning (DL) methods have improved drastically the quality of SR generated images. However, these qualitative improvements are not always followed by quantitative improvements in the traditional metrics of the area, namely PSNR (Peak Signal-to-Noise Ratio) and SSIM (Structural Similarity Index). In some cases, models that perform better in opinion scores and qualitative evaluation have worse performance in these metrics, indicating they are not sufficiently informative. To address this issue we propose a task-based evaluation procedure based on the comparative performance of face recognition algorithms on HR and SR images to evaluate how well the models retrieve high-frequency and identity defining information. Furthermore, as our face recognition model is differentiable, this leads to a novel loss function that can be optimized to improve performance in these tasks. We successfully apply our evaluation method to validate this training method, yielding promising results.
Arrangement 1urlib.net > SDLA > Fonds > SIBGRAPI 2019 > Optimizing Super Resolution...
Arrangement 2urlib.net > SDLA > Fonds > Full Index > Optimizing Super Resolution...
doc Directory Contentaccess
source Directory Contentthere are no files
agreement Directory Content
agreement.html 09/09/2019 17:40 1.2 KiB 
4. Conditions of access and use
data URLhttp://urlib.net/ibi/8JMKD3MGPEW34M/3U2JUJH
zipped data URLhttp://urlib.net/zip/8JMKD3MGPEW34M/3U2JUJH
Languageen
Target Filecamera-ready.pdf
User Groupabello@ime.usp.br
Visibilityshown
Update Permissionnot transferred
5. Allied materials
Mirror Repositorysid.inpe.br/banon/2001/03.30.15.38.24
Next Higher Units8JMKD3MGPEW34M/3UA4FNL
8JMKD3MGPEW34M/3UA4FPS
8JMKD3MGPEW34M/4742MCS
Citing Item Listsid.inpe.br/sibgrapi/2019/10.25.18.30.33 25
sid.inpe.br/sibgrapi/2022/06.10.21.49 7
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
7. Description control
e-Mail (login)abello@ime.usp.br
update 


Close