Pixel‐wise supervision for presentation attack detection on identity document cards

Abstract Identity documents (or IDs) play an important role in verifying the identity of a person with wide applications in banks, travel, video‐identification services and border controls. Replay or photocopied ID cards can be misused to pass ID control in unsupervised scenarios if the liveness of...

Full description

Saved in:
Bibliographic Details
Main Authors: Raghavendra Mudgalgundurao, Patrick Schuch, Kiran Raja, Raghavendra Ramachandra, Naser Damer
Format: Article
Language:English
Published: Wiley 2022-09-01
Series:IET Biometrics
Online Access:https://doi.org/10.1049/bme2.12088
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832559616274202624
author Raghavendra Mudgalgundurao
Patrick Schuch
Kiran Raja
Raghavendra Ramachandra
Naser Damer
author_facet Raghavendra Mudgalgundurao
Patrick Schuch
Kiran Raja
Raghavendra Ramachandra
Naser Damer
author_sort Raghavendra Mudgalgundurao
collection DOAJ
description Abstract Identity documents (or IDs) play an important role in verifying the identity of a person with wide applications in banks, travel, video‐identification services and border controls. Replay or photocopied ID cards can be misused to pass ID control in unsupervised scenarios if the liveness of a person is not checked. To detect such presentation attacks on ID card verification process when presented virtually is a critical step for the biometric systems to assure authenticity. In this paper, a pixel‐wise supervision on DenseNet is proposed to detect presentation attacks of the printed and digitally replayed attacks. The authors motivate the approach to use pixel‐wise supervision to leverage minute cues on various artefacts such as moiré patterns and artefacts left by the printers. The baseline benchmark is presented using different handcrafted and deep learning models on a newly constructed in‐house database obtained from an operational system consisting of 886 users with 433 bona fide, 67 print and 366 display attacks. It is demonstrated that the proposed approach achieves better performance compared to handcrafted features and Deep Models with an Equal Error Rate of 2.22% and Bona fide Presentation Classification Error Rate (BPCER) of 1.83% and 1.67% at Attack Presentation Classification Error Rate of 5% and 10%.
format Article
id doaj-art-3bf9b73c00754f089513571671c46292
institution Kabale University
issn 2047-4938
2047-4946
language English
publishDate 2022-09-01
publisher Wiley
record_format Article
series IET Biometrics
spelling doaj-art-3bf9b73c00754f089513571671c462922025-02-03T01:29:39ZengWileyIET Biometrics2047-49382047-49462022-09-0111538339510.1049/bme2.12088Pixel‐wise supervision for presentation attack detection on identity document cardsRaghavendra Mudgalgundurao0Patrick Schuch1Kiran Raja2Raghavendra Ramachandra3Naser Damer4Nect GmbH Hamburg GermanyNect GmbH Hamburg GermanyNTNU ‐ Gjøvik Gjøvik NorwayNTNU ‐ Gjøvik Gjøvik NorwayFraunhofer IGD Darmstadt GermanyAbstract Identity documents (or IDs) play an important role in verifying the identity of a person with wide applications in banks, travel, video‐identification services and border controls. Replay or photocopied ID cards can be misused to pass ID control in unsupervised scenarios if the liveness of a person is not checked. To detect such presentation attacks on ID card verification process when presented virtually is a critical step for the biometric systems to assure authenticity. In this paper, a pixel‐wise supervision on DenseNet is proposed to detect presentation attacks of the printed and digitally replayed attacks. The authors motivate the approach to use pixel‐wise supervision to leverage minute cues on various artefacts such as moiré patterns and artefacts left by the printers. The baseline benchmark is presented using different handcrafted and deep learning models on a newly constructed in‐house database obtained from an operational system consisting of 886 users with 433 bona fide, 67 print and 366 display attacks. It is demonstrated that the proposed approach achieves better performance compared to handcrafted features and Deep Models with an Equal Error Rate of 2.22% and Bona fide Presentation Classification Error Rate (BPCER) of 1.83% and 1.67% at Attack Presentation Classification Error Rate of 5% and 10%.https://doi.org/10.1049/bme2.12088
spellingShingle Raghavendra Mudgalgundurao
Patrick Schuch
Kiran Raja
Raghavendra Ramachandra
Naser Damer
Pixel‐wise supervision for presentation attack detection on identity document cards
IET Biometrics
title Pixel‐wise supervision for presentation attack detection on identity document cards
title_full Pixel‐wise supervision for presentation attack detection on identity document cards
title_fullStr Pixel‐wise supervision for presentation attack detection on identity document cards
title_full_unstemmed Pixel‐wise supervision for presentation attack detection on identity document cards
title_short Pixel‐wise supervision for presentation attack detection on identity document cards
title_sort pixel wise supervision for presentation attack detection on identity document cards
url https://doi.org/10.1049/bme2.12088
work_keys_str_mv AT raghavendramudgalgundurao pixelwisesupervisionforpresentationattackdetectiononidentitydocumentcards
AT patrickschuch pixelwisesupervisionforpresentationattackdetectiononidentitydocumentcards
AT kiranraja pixelwisesupervisionforpresentationattackdetectiononidentitydocumentcards
AT raghavendraramachandra pixelwisesupervisionforpresentationattackdetectiononidentitydocumentcards
AT naserdamer pixelwisesupervisionforpresentationattackdetectiononidentitydocumentcards