Home > Research > Publications & Outputs > Perceptual and computational detection of face ...

Associated organisational unit

Links

Text available via DOI:

View graph of relations

Perceptual and computational detection of face morphing

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Published

Standard

Perceptual and computational detection of face morphing. / Nightingale, Sophie J; Agarwal, Shruti; Farid, Hany.

In: Journal of Vision, Vol. 21, No. 3, 4, 31.03.2021, p. 1-18.

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Harvard

Nightingale, SJ, Agarwal, S & Farid, H 2021, 'Perceptual and computational detection of face morphing', Journal of Vision, vol. 21, no. 3, 4, pp. 1-18. https://doi.org/10.1167/jov.21.3.4

APA

Nightingale, S. J., Agarwal, S., & Farid, H. (2021). Perceptual and computational detection of face morphing. Journal of Vision, 21(3), 1-18. [4]. https://doi.org/10.1167/jov.21.3.4

Vancouver

Nightingale SJ, Agarwal S, Farid H. Perceptual and computational detection of face morphing. Journal of Vision. 2021 Mar 31;21(3):1-18. 4. https://doi.org/10.1167/jov.21.3.4

Author

Nightingale, Sophie J ; Agarwal, Shruti ; Farid, Hany. / Perceptual and computational detection of face morphing. In: Journal of Vision. 2021 ; Vol. 21, No. 3. pp. 1-18.

Bibtex

@article{57692a05e5e54bedac0e8ebe1de3ec32,
title = "Perceptual and computational detection of face morphing",
abstract = "A relatively new type of identity theft uses morphed facial images in identification documents in which images of two individuals are digitally blended to create an image that maintains a likeness to each of the original identities. We created a set of high-quality digital morphs from passport-style photos for a diverse set of people across gender, race, and age. We then examine people{\textquoteright}s ability to detect facial morphing both in terms of determining if two side-by-side faces are of the same individual or not and in terms of identifying if a face is the result of digital morphing. We show that human participants struggle at both tasks. Even modern machine-learning-based facial recognition struggles to distinguish between an individual and their morphed version. We conclude with a hopeful note, describing a computational technique that holds some promise in recognizing that one facial image is a morphed version of another.",
author = "Nightingale, {Sophie J} and Shruti Agarwal and Hany Farid",
year = "2021",
month = mar,
day = "31",
doi = "10.1167/jov.21.3.4",
language = "English",
volume = "21",
pages = "1--18",
journal = "Journal of Vision",
issn = "1534-7362",
publisher = "Association for Research in Vision and Ophthalmology Inc.",
number = "3",

}

RIS

TY - JOUR

T1 - Perceptual and computational detection of face morphing

AU - Nightingale, Sophie J

AU - Agarwal, Shruti

AU - Farid, Hany

PY - 2021/3/31

Y1 - 2021/3/31

N2 - A relatively new type of identity theft uses morphed facial images in identification documents in which images of two individuals are digitally blended to create an image that maintains a likeness to each of the original identities. We created a set of high-quality digital morphs from passport-style photos for a diverse set of people across gender, race, and age. We then examine people’s ability to detect facial morphing both in terms of determining if two side-by-side faces are of the same individual or not and in terms of identifying if a face is the result of digital morphing. We show that human participants struggle at both tasks. Even modern machine-learning-based facial recognition struggles to distinguish between an individual and their morphed version. We conclude with a hopeful note, describing a computational technique that holds some promise in recognizing that one facial image is a morphed version of another.

AB - A relatively new type of identity theft uses morphed facial images in identification documents in which images of two individuals are digitally blended to create an image that maintains a likeness to each of the original identities. We created a set of high-quality digital morphs from passport-style photos for a diverse set of people across gender, race, and age. We then examine people’s ability to detect facial morphing both in terms of determining if two side-by-side faces are of the same individual or not and in terms of identifying if a face is the result of digital morphing. We show that human participants struggle at both tasks. Even modern machine-learning-based facial recognition struggles to distinguish between an individual and their morphed version. We conclude with a hopeful note, describing a computational technique that holds some promise in recognizing that one facial image is a morphed version of another.

U2 - 10.1167/jov.21.3.4

DO - 10.1167/jov.21.3.4

M3 - Journal article

VL - 21

SP - 1

EP - 18

JO - Journal of Vision

JF - Journal of Vision

SN - 1534-7362

IS - 3

M1 - 4

ER -