hh.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
On the effect of selfie beautification filters on face detection and recognition
Halmstad University, School of Information Technology.
Halmstad University, School of Information Technology.
Halmstad University, School of Information Technology.ORCID iD: 0000-0002-9696-7843
Halmstad University, School of Information Technology.ORCID iD: 0000-0002-4929-1262
Show others and affiliations
2022 (English)In: Pattern Recognition Letters, ISSN 0167-8655, E-ISSN 1872-7344, Vol. 163, p. 104-111Article in journal (Refereed) Published
Abstract [en]

Beautification and augmented reality filters are very popular in applications that use selfie images. However, they can distort or modify biometric features, severely affecting the ability to recognise the individuals’ identity or even detect the face. Accordingly, we address the effect of such filters on the accuracy of automated face detection and recognition. The social media image filters studied modify the image contrast, illumination, or occlude parts of the face. We observe that the effect of some of these filters is harmful to face detection and identity recognition, especially if they obfuscate the eye or (to a lesser extent) the nose. To counteract such effect, we develop a method to reverse the applied manipulation with a modified version of the U-NET segmentation network. This method is observed to contribute to better face detection and recognition accuracy. From a recognition perspective, we employ distance measures and trained machine learning algorithms applied to features extracted using several CNN backbones. We also evaluate if incorporating filtered images into the training set of machine learning approaches is beneficial. Our results show good recognition when filters do not occlude important landmarks, especially the eyes. The combined effect of the proposed approaches also allows mitigating the impact produced by filters that occlude parts of the face. © 2022 The Authors. Published by Elsevier B.V.

Place, publisher, year, edition, pages
Amsterdam: Elsevier, 2022. Vol. 163, p. 104-111
Keywords [en]
Face detection, Face recognition, Social media filters, Beautification, U-NET, Convolutional neural network
National Category
Signal Processing
Identifiers
URN: urn:nbn:se:hh:diva-48481DOI: 10.1016/j.patrec.2022.09.018ISI: 000877215000005Scopus ID: 2-s2.0-85139592291OAI: oai:DiVA.org:hh-48481DiVA, id: diva2:1703835
Part of project
Facial Analysis in the Era of Mobile Devices and Face Masks, Swedish Research Council
Funder
Swedish Research CouncilVinnovaAvailable from: 2022-10-14 Created: 2022-10-14 Last updated: 2024-06-17Bibliographically approved

Open Access in DiVA

fulltext(2212 kB)244 downloads
File information
File name FULLTEXT01.pdfFile size 2212 kBChecksum SHA-512
88fe95404e61536ee38eef37902f5fab3370afaf9bd3d8a937462385f57b82a37382731901c36610041bea124fa557839af175064cab86c0abac314293a81378
Type fulltextMimetype application/pdf

Other links

Publisher's full textScopus

Authority records

Hernandez-Diaz, KevinBigun, JosefAlonso-Fernandez, Fernando

Search in DiVA

By author/editor
Hedman, PontusSkepetzis, VasiliosHernandez-Diaz, KevinBigun, JosefAlonso-Fernandez, Fernando
By organisation
School of Information Technology
In the same journal
Pattern Recognition Letters
Signal Processing

Search outside of DiVA

GoogleGoogle Scholar
Total: 244 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 612 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf