Nowadays, face morphing represents a big security threat in the context of electronic identity documents as well as an interesting challenge for researchers in the field of face recognition. Despite the good performance obtained by state-of-the-art approaches on digital images, no satisfactory solutions have been identified so far to deal with cross-database testing and printed-scanned images (typically used in many countries for document issuing).To solve this problem, the authors propose new approaches to train Deep Neural Networks for morphing attack detection: in particular the generation of simulated printed-scanned images together with other data augmentation strategies and pre-training on large face recognition datasets, allowed reaching state-of-the-art accuracy on challenging datasets from heterogeneous image sources.

Face morphing detection in the presence of printing/scanning and heterogeneous image sources

Ferrara, Matteo
;
Franco, Annalisa;Maltoni, Davide
2021

Abstract

Nowadays, face morphing represents a big security threat in the context of electronic identity documents as well as an interesting challenge for researchers in the field of face recognition. Despite the good performance obtained by state-of-the-art approaches on digital images, no satisfactory solutions have been identified so far to deal with cross-database testing and printed-scanned images (typically used in many countries for document issuing).To solve this problem, the authors propose new approaches to train Deep Neural Networks for morphing attack detection: in particular the generation of simulated printed-scanned images together with other data augmentation strategies and pre-training on large face recognition datasets, allowed reaching state-of-the-art accuracy on challenging datasets from heterogeneous image sources.
Ferrara, Matteo; Franco, Annalisa; Maltoni, Davide
File in questo prodotto:
File Dimensione Formato  
bme2.12021.pdf

accesso aperto

Tipo: Versione (PDF) editoriale
Licenza: Licenza per Accesso Aperto. Creative Commons Attribuzione - Non commerciale - Non opere derivate (CCBYNCND)
Dimensione 2.05 MB
Formato Adobe PDF
2.05 MB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11585/855985
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? 8
social impact