Facial recognition from DNA using face-to-DNA classifiers

Dzemila Sero; Arslan Zaidi; Jiarui Li; Julie D. White; Tomás B.González Zarzar; Mary L. Marazita; Seth M. Weinberg; Paul Suetens; Dirk Vandermeulen; Jennifer K. Wagner; Mark D. Shriver; Peter Claes

doi:10.1038/s41467-019-10617-y

Facial recognition from DNA using face-to-DNA classifiers

Dzemila Sero, Arslan Zaidi, Jiarui Li, Julie D. White, Tomás B.González Zarzar, Mary L. Marazita, Seth M. Weinberg, Paul Suetens, Dirk Vandermeulen, Jennifer K. Wagner, Mark D. Shriver, Peter Claes

Research output: Contribution to journal › Article › peer-review

39 Scopus citations

Abstract

Facial recognition from DNA refers to the identification or verification of unidentified biological material against facial images with known identity. One approach to establish the identity of unidentified biological material is to predict the face from DNA, and subsequently to match against facial images. However, DNA phenotyping of the human face remains challenging. Here, another proof of concept to biometric authentication is established by using multiple face-to-DNA classifiers, each classifying given faces by a DNA-encoded aspect (sex, genomic background, individual genetic loci), or by a DNA-inferred aspect (BMI, age). Face-to-DNA classifiers on distinct DNA aspects are fused into one matching score for any given face against DNA. In a globally diverse, and subsequently in a homogeneous cohort, we demonstrate preliminary, but substantial true (83%, 80%) over false (17%, 20%) matching in verification mode. Consequences of future efforts include forensic applications, necessitating careful consideration of ethical and legal implications for privacy in genomic databases.

Original language	English (US)
Article number	2557
Journal	Nature communications
Volume	10
Issue number	1
DOIs	https://doi.org/10.1038/s41467-019-10617-y
State	Published - Dec 1 2019
Externally published	Yes

Bibliographical note

Funding Information:
This investigation was supported by the KU Leuven, BOF (C14/15/081), NIH (1-RO1-DE027023) and FWO Flanders (G078518N). The collaborators at the Penn State University were supported in part by grants from the Center for Human Evolution and Development at Penn State, the Science Foundation of Ireland Walton Fellowship (04. W4/B643), the United States National Institute Justice (www.nij.gov; 2008-DN-BX-K125), and by the United States Department of Defense (www.defense.gov). JKW’s contribution was supported by Grant No. R00HG006446 from the National Human Genome Research Institute. The collaborators at the University of Pittsburgh were supported by grants from the National Institute for Dental and Craniofacial Research (http://www.nidcr.nih.gov/) (U01-DE020078; R01-DE027023; R01-DE016148; 1-R01-DE027023) and the Centers for Disease Control (https://www.cdc.gov/) (R01-DD000295). Funding for genotyping of the PITT cohort was provided by the National Human Genome Research Institute (https://www.genome.gov/): X01-HG007821. The content of this article is the authors’ responsibilities and might not represent the official views of the authors’ funding sources or employers.

Publisher Copyright:
© 2019, The Author(s).

Publisher link

10.1038/s41467-019-10617-y

Find It

Find It at U of M Libraries

Cite this

@article{547fd829248f4b0f8e8517c5a77c3673,

title = "Facial recognition from DNA using face-to-DNA classifiers",

abstract = "Facial recognition from DNA refers to the identification or verification of unidentified biological material against facial images with known identity. One approach to establish the identity of unidentified biological material is to predict the face from DNA, and subsequently to match against facial images. However, DNA phenotyping of the human face remains challenging. Here, another proof of concept to biometric authentication is established by using multiple face-to-DNA classifiers, each classifying given faces by a DNA-encoded aspect (sex, genomic background, individual genetic loci), or by a DNA-inferred aspect (BMI, age). Face-to-DNA classifiers on distinct DNA aspects are fused into one matching score for any given face against DNA. In a globally diverse, and subsequently in a homogeneous cohort, we demonstrate preliminary, but substantial true (83%, 80%) over false (17%, 20%) matching in verification mode. Consequences of future efforts include forensic applications, necessitating careful consideration of ethical and legal implications for privacy in genomic databases.",

author = "Dzemila Sero and Arslan Zaidi and Jiarui Li and White, {Julie D.} and Zarzar, {Tom{\'a}s B.Gonz{\'a}lez} and Marazita, {Mary L.} and Weinberg, {Seth M.} and Paul Suetens and Dirk Vandermeulen and Wagner, {Jennifer K.} and Shriver, {Mark D.} and Peter Claes",

note = "Funding Information: This investigation was supported by the KU Leuven, BOF (C14/15/081), NIH (1-RO1-DE027023) and FWO Flanders (G078518N). The collaborators at the Penn State University were supported in part by grants from the Center for Human Evolution and Development at Penn State, the Science Foundation of Ireland Walton Fellowship (04. W4/B643), the United States National Institute Justice (www.nij.gov; 2008-DN-BX-K125), and by the United States Department of Defense (www.defense.gov). JKW{\textquoteright}s contribution was supported by Grant No. R00HG006446 from the National Human Genome Research Institute. The collaborators at the University of Pittsburgh were supported by grants from the National Institute for Dental and Craniofacial Research (http://www.nidcr.nih.gov/) (U01-DE020078; R01-DE027023; R01-DE016148; 1-R01-DE027023) and the Centers for Disease Control (https://www.cdc.gov/) (R01-DD000295). Funding for genotyping of the PITT cohort was provided by the National Human Genome Research Institute (https://www.genome.gov/): X01-HG007821. The content of this article is the authors{\textquoteright} responsibilities and might not represent the official views of the authors{\textquoteright} funding sources or employers. Publisher Copyright: {\textcopyright} 2019, The Author(s).",

year = "2019",

month = dec,

day = "1",

doi = "10.1038/s41467-019-10617-y",

language = "English (US)",

volume = "10",

journal = "Nature communications",

issn = "2041-1723",

publisher = "Nature Publishing Group",

number = "1",

}

TY - JOUR

T1 - Facial recognition from DNA using face-to-DNA classifiers

AU - Sero, Dzemila

AU - Zaidi, Arslan

AU - Li, Jiarui

AU - White, Julie D.

AU - Zarzar, Tomás B.González

AU - Marazita, Mary L.

AU - Weinberg, Seth M.

AU - Suetens, Paul

AU - Vandermeulen, Dirk

AU - Wagner, Jennifer K.

AU - Shriver, Mark D.

AU - Claes, Peter

N1 - Funding Information: This investigation was supported by the KU Leuven, BOF (C14/15/081), NIH (1-RO1-DE027023) and FWO Flanders (G078518N). The collaborators at the Penn State University were supported in part by grants from the Center for Human Evolution and Development at Penn State, the Science Foundation of Ireland Walton Fellowship (04. W4/B643), the United States National Institute Justice (www.nij.gov; 2008-DN-BX-K125), and by the United States Department of Defense (www.defense.gov). JKW’s contribution was supported by Grant No. R00HG006446 from the National Human Genome Research Institute. The collaborators at the University of Pittsburgh were supported by grants from the National Institute for Dental and Craniofacial Research (http://www.nidcr.nih.gov/) (U01-DE020078; R01-DE027023; R01-DE016148; 1-R01-DE027023) and the Centers for Disease Control (https://www.cdc.gov/) (R01-DD000295). Funding for genotyping of the PITT cohort was provided by the National Human Genome Research Institute (https://www.genome.gov/): X01-HG007821. The content of this article is the authors’ responsibilities and might not represent the official views of the authors’ funding sources or employers. Publisher Copyright: © 2019, The Author(s).

PY - 2019/12/1

Y1 - 2019/12/1

N2 - Facial recognition from DNA refers to the identification or verification of unidentified biological material against facial images with known identity. One approach to establish the identity of unidentified biological material is to predict the face from DNA, and subsequently to match against facial images. However, DNA phenotyping of the human face remains challenging. Here, another proof of concept to biometric authentication is established by using multiple face-to-DNA classifiers, each classifying given faces by a DNA-encoded aspect (sex, genomic background, individual genetic loci), or by a DNA-inferred aspect (BMI, age). Face-to-DNA classifiers on distinct DNA aspects are fused into one matching score for any given face against DNA. In a globally diverse, and subsequently in a homogeneous cohort, we demonstrate preliminary, but substantial true (83%, 80%) over false (17%, 20%) matching in verification mode. Consequences of future efforts include forensic applications, necessitating careful consideration of ethical and legal implications for privacy in genomic databases.

AB - Facial recognition from DNA refers to the identification or verification of unidentified biological material against facial images with known identity. One approach to establish the identity of unidentified biological material is to predict the face from DNA, and subsequently to match against facial images. However, DNA phenotyping of the human face remains challenging. Here, another proof of concept to biometric authentication is established by using multiple face-to-DNA classifiers, each classifying given faces by a DNA-encoded aspect (sex, genomic background, individual genetic loci), or by a DNA-inferred aspect (BMI, age). Face-to-DNA classifiers on distinct DNA aspects are fused into one matching score for any given face against DNA. In a globally diverse, and subsequently in a homogeneous cohort, we demonstrate preliminary, but substantial true (83%, 80%) over false (17%, 20%) matching in verification mode. Consequences of future efforts include forensic applications, necessitating careful consideration of ethical and legal implications for privacy in genomic databases.

UR - http://www.scopus.com/inward/record.url?scp=85067246497&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85067246497&partnerID=8YFLogxK

U2 - 10.1038/s41467-019-10617-y

DO - 10.1038/s41467-019-10617-y

M3 - Article

C2 - 31186421

AN - SCOPUS:85067246497

SN - 2041-1723

VL - 10

JO - Nature communications

JF - Nature communications

IS - 1

M1 - 2557

ER -

Facial recognition from DNA using face-to-DNA classifiers

Abstract

Bibliographical note

Publisher link

Find It

Other files and links

Fingerprint

Cite this