hh.sePublikationer
Ändra sökning
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Facial Masks and Soft-Biometrics: Leveraging Face Recognition CNNs for Age and Gender Prediction on Mobile Ocular Images
Högskolan i Halmstad, Akademin för informationsteknologi, Halmstad Embedded and Intelligent Systems Research (EIS), CAISR Centrum för tillämpade intelligenta system (IS-lab).ORCID-id: 0000-0002-1400-346X
Högskolan i Halmstad, Akademin för informationsteknologi, Halmstad Embedded and Intelligent Systems Research (EIS), CAISR Centrum för tillämpade intelligenta system (IS-lab).
Computer Graphics and Vision and AI Group, University of Balearic Islands, Spain.
Computer Graphics and Vision and AI Group, University of Balearic Islands, Spain.
Visa övriga samt affilieringar
2021 (Engelska)Ingår i: IET Biometrics, ISSN 2047-4938, E-ISSN 2047-4946, Vol. 10, nr 5, s. 562-580Artikel i tidskrift (Refereegranskat) Published
Abstract [en]

We address the use of selfie ocular images captured with smartphones to estimate age and gender. Partial face occlusion has become an issue due to the mandatory use of face masks. Also, the use of mobile devices has exploded, with the pandemic further accelerating the migration to digital services. However, state-of-the-art solutions in related tasks such as identity or expression recognition employ large Convolutional Neural Networks, whose use in mobile devices is infeasible due to hardware limitations and size restrictions of downloadable applications. To counteract this, we adapt two existing lightweight CNNs proposed in the context of the ImageNet Challenge, and two additional architectures proposed for mobile face recognition. Since datasets for soft-biometrics prediction using selfie images are limited, we counteract over-fitting by using networks pre-trained on ImageNet. Furthermore, some networks are further pre-trained for face recognition, for which very large training databases are available. Since both tasks employ similar input data, we hypothesize that such strategy can be beneficial for soft-biometrics estimation. A comprehensive study of the effects of different pre-training over the employed architectures is carried out, showing that, in most cases, a better accuracy is obtained after the networks have been fine-tuned for face recognition. © The Authors

Ort, förlag, år, upplaga, sidor
Stevenage: Institution of Engineering and Technology, 2021. Vol. 10, nr 5, s. 562-580
Nationell ämneskategori
Signalbehandling Datorseende och robotik (autonoma system)
Identifikatorer
URN: urn:nbn:se:hh:diva-44262DOI: 10.1049/bme2.12046ISI: 000661520100001Scopus ID: 2-s2.0-85108707251OAI: oai:DiVA.org:hh-44262DiVA, id: diva2:1549146
Ingår i projekt
Okulär biometrik i naturliga miljöer, Vetenskapsrådet
Forskningsfinansiär
Vetenskapsrådet, 2016-03497
Anmärkning

Funding: Part of this research has been enabled by a visiting position of F. Alonso-Fernandez at the University of the Balearic Islands (UIB), funded by the UIB visiting lecturers program. Authors F. Alonso-Fernandez, K. Hernandez-Diaz and J. Bigun would like to thank the Swedish Research Council for funding their research. Authors F. J. Perales and S. Ramis would like to thank the projects PERGAMEX RTI2018-096986-B-C31 (MINECO/AEI/ ERDF, EU) and PID2019-104829RA-I00 / AEI / 10.13039/501100011033 (MICINN).

Tillgänglig från: 2021-05-04 Skapad: 2021-05-04 Senast uppdaterad: 2023-06-08Bibliografiskt granskad

Open Access i DiVA

fulltext(1542 kB)188 nedladdningar
Filinformation
Filnamn FULLTEXT02.pdfFilstorlek 1542 kBChecksumma SHA-512
8fcaa7a6a494d153e5ee222a8a6e767908ba8954e92a2099ef2be3def2ed085fa875fa8ade598e830b2b59f640403b83a55ce34649c62a7948d11dc46d9d9c7f
Typ fulltextMimetyp application/pdf

Övriga länkar

Förlagets fulltextScopusFull text

Person

Alonso-Fernandez, FernandoHernandez-Diaz, KevinBigun, Josef

Sök vidare i DiVA

Av författaren/redaktören
Alonso-Fernandez, FernandoHernandez-Diaz, KevinBigun, Josef
Av organisationen
CAISR Centrum för tillämpade intelligenta system (IS-lab)
I samma tidskrift
IET Biometrics
SignalbehandlingDatorseende och robotik (autonoma system)

Sök vidare utanför DiVA

GoogleGoogle Scholar
Totalt: 195 nedladdningar
Antalet nedladdningar är summan av nedladdningar för alla fulltexter. Det kan inkludera t.ex tidigare versioner som nu inte längre är tillgängliga.

doi
urn-nbn

Altmetricpoäng

doi
urn-nbn
Totalt: 369 träffar
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf