Kinship verification from facial images and videos: human versus machine

Miguel Bordallo Lopez, Abdenour Hadid, Elhocine Boutellaa, Jorge Goncalves, Vassilis Kostakos, Simo Hosio

Research output: Contribution to journalArticleScientificpeer-review

4 Citations (Scopus)

Abstract

Automatic kinship verification from facial images is a relatively new and challenging research problem in computer vision. It consists in automatically determining whether two persons have a biological kin relation by examining their facial attributes. In this work, we compare the performance of humans and machines in kinship verification tasks. We investigate the state-of-the-art methods in automatic kinship verification from facial images, comparing their performance with the one obtained by asking humans to complete an equivalent task using a crowdsourcing system. Our results show that machines can consistently beat humans in kinship classification tasks in both images and videos. In addition, we study the limitations of currently available kinship databases and analyzing their possible impact in kinship verification experiment and this type of comparison.
Original languageEnglish
Pages (from-to)873 – 890
Number of pages18
JournalMachine Vision and Applications
Volume29
Issue number5
DOIs
Publication statusPublished - Jul 2018
MoE publication typeA1 Journal article-refereed

Fingerprint

Computer vision
Experiments

Keywords

  • kinship verification
  • face analysis
  • biometrics
  • crowdsourcing

Cite this

Bordallo Lopez, Miguel ; Hadid, Abdenour ; Boutellaa, Elhocine ; Goncalves, Jorge ; Kostakos, Vassilis ; Hosio, Simo. / Kinship verification from facial images and videos : human versus machine. In: Machine Vision and Applications. 2018 ; Vol. 29, No. 5. pp. 873 – 890.
@article{531ded010837420e94438906785e01e1,
title = "Kinship verification from facial images and videos: human versus machine",
abstract = "Automatic kinship verification from facial images is a relatively new and challenging research problem in computer vision. It consists in automatically determining whether two persons have a biological kin relation by examining their facial attributes. In this work, we compare the performance of humans and machines in kinship verification tasks. We investigate the state-of-the-art methods in automatic kinship verification from facial images, comparing their performance with the one obtained by asking humans to complete an equivalent task using a crowdsourcing system. Our results show that machines can consistently beat humans in kinship classification tasks in both images and videos. In addition, we study the limitations of currently available kinship databases and analyzing their possible impact in kinship verification experiment and this type of comparison.",
keywords = "kinship verification, face analysis, biometrics, crowdsourcing",
author = "{Bordallo Lopez}, Miguel and Abdenour Hadid and Elhocine Boutellaa and Jorge Goncalves and Vassilis Kostakos and Simo Hosio",
year = "2018",
month = "7",
doi = "10.1007/s00138-018-0943-x",
language = "English",
volume = "29",
pages = "873 – 890",
journal = "Machine Vision and Applications",
issn = "0932-8092",
publisher = "Springer",
number = "5",

}

Bordallo Lopez, M, Hadid, A, Boutellaa, E, Goncalves, J, Kostakos, V & Hosio, S 2018, 'Kinship verification from facial images and videos: human versus machine', Machine Vision and Applications, vol. 29, no. 5, pp. 873 – 890. https://doi.org/10.1007/s00138-018-0943-x

Kinship verification from facial images and videos : human versus machine. / Bordallo Lopez, Miguel; Hadid, Abdenour; Boutellaa, Elhocine; Goncalves, Jorge; Kostakos, Vassilis; Hosio, Simo.

In: Machine Vision and Applications, Vol. 29, No. 5, 07.2018, p. 873 – 890.

Research output: Contribution to journalArticleScientificpeer-review

TY - JOUR

T1 - Kinship verification from facial images and videos

T2 - human versus machine

AU - Bordallo Lopez, Miguel

AU - Hadid, Abdenour

AU - Boutellaa, Elhocine

AU - Goncalves, Jorge

AU - Kostakos, Vassilis

AU - Hosio, Simo

PY - 2018/7

Y1 - 2018/7

N2 - Automatic kinship verification from facial images is a relatively new and challenging research problem in computer vision. It consists in automatically determining whether two persons have a biological kin relation by examining their facial attributes. In this work, we compare the performance of humans and machines in kinship verification tasks. We investigate the state-of-the-art methods in automatic kinship verification from facial images, comparing their performance with the one obtained by asking humans to complete an equivalent task using a crowdsourcing system. Our results show that machines can consistently beat humans in kinship classification tasks in both images and videos. In addition, we study the limitations of currently available kinship databases and analyzing their possible impact in kinship verification experiment and this type of comparison.

AB - Automatic kinship verification from facial images is a relatively new and challenging research problem in computer vision. It consists in automatically determining whether two persons have a biological kin relation by examining their facial attributes. In this work, we compare the performance of humans and machines in kinship verification tasks. We investigate the state-of-the-art methods in automatic kinship verification from facial images, comparing their performance with the one obtained by asking humans to complete an equivalent task using a crowdsourcing system. Our results show that machines can consistently beat humans in kinship classification tasks in both images and videos. In addition, we study the limitations of currently available kinship databases and analyzing their possible impact in kinship verification experiment and this type of comparison.

KW - kinship verification

KW - face analysis

KW - biometrics

KW - crowdsourcing

UR - http://www.scopus.com/inward/record.url?scp=85047667915&partnerID=8YFLogxK

U2 - 10.1007/s00138-018-0943-x

DO - 10.1007/s00138-018-0943-x

M3 - Article

VL - 29

SP - 873

EP - 890

JO - Machine Vision and Applications

JF - Machine Vision and Applications

SN - 0932-8092

IS - 5

ER -