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
Unsupervised Facial Biometric Data Filtering for Age and Gender Estimation
Faculty of Electrical Engineering and Computing, University of Zagreb,.ORCID-id: 0000-0002-5861-7076
Linköpings universitet, Institutionen för systemteknik, Datorseende. Linköpings universitet, Tekniska fakulteten.ORCID-id: 0000-0002-6763-5487
Faculty of Electrical Engineering and Computing, University of Zagreb.
2019 (Engelska)Ingår i: Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2019), SciTePress, 2019, Vol. 5, s. 209-217Konferensbidrag, Publicerat paper (Refereegranskat)
Abstract [en]

Availability of large training datasets was essential for the recent advancement and success of deep learning methods. Due to the difficulties related to biometric data collection, datasets with age and gender annotations are scarce and usually limited in terms of size and sample diversity. Web-scraping approaches for automatic data collection can produce large amounts weakly labeled noisy data. The unsupervised facial biometric data filtering method presented in this paper greatly reduces label noise levels in web-scraped facial biometric data. Experiments on two large state-of-the-art web-scraped facial datasets demonstrate the effectiveness of the proposed method, with respect to training and validation scores, training convergence, and generalization capabilities of trained age and gender estimators.

Ort, förlag, år, upplaga, sidor
SciTePress, 2019. Vol. 5, s. 209-217
Nyckelord [en]
Biometric, Web-Scraping, Age, Gender
Nationell ämneskategori
Datorseende och robotik (autonoma system)
Identifikatorer
URN: urn:nbn:se:liu:diva-154867ISBN: 978-989-758-354-4 (digital)OAI: oai:DiVA.org:liu-154867DiVA, id: diva2:1292960
Konferens
International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications
Tillgänglig från: 2019-03-01 Skapad: 2019-03-01 Senast uppdaterad: 2019-04-03

Open Access i DiVA

Fulltext saknas i DiVA

Sök vidare i DiVA

Av författaren/redaktören
Bešenić, KrešimirAhlberg, Jörgen
Av organisationen
DatorseendeTekniska fakulteten
Datorseende och robotik (autonoma system)

Sök vidare utanför DiVA

GoogleGoogle Scholar

isbn
urn-nbn

Altmetricpoäng

isbn
urn-nbn
Totalt: 679 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