Does Melania Trump have a body double from the perspective of automatic face verification?

Mallat, Khawla; Becerra-Riera, Fabiola; Morales-Gonzalez, Annette; Mendez-Vazquez, Heydi; Dugelay, Jean-Luc
ICPRAM 2022, 11th International Conference on Pattern Recognition Applications and Methods, in conjunction with ICAART 2022, 3-5 February (Online Event)

With the growing number of users getting updated about current events through social media, the spread of misinformation is increasing and thus endorsing conspiracy belief. During the last presidential election campaign in the USA, the conspiracy theory claiming the existence of a body double that stands in for the former first lady Melania Trump had made international news headlines. Fighting the spread of misinformation is crucial as it is threatening the society by manipulating the public opinion. In this paper, we explore whether automatic face verification can help in verifying widespread misinformation on social media, dealing particularly with the conspiracy theory related to Melania Trump replacement. We employed four different state-of-the-art descriptors for face recognition to verify the integrity of the claim of the studied conspiracy theory. In addition, we assessed the impact of different image quality metrics on the variation of the face verification scores. Two sets of image quality metrics were considered: acquisition-related metrics and subject-related metrics.

DOI
Type:
Conference
Date:
2022-02-03
Department:
Digital Security
Eurecom Ref:
6806
Copyright:
© Insticc. Personal use of this material is permitted. The definitive version of this paper was published in ICPRAM 2022, 11th International Conference on Pattern Recognition Applications and Methods, in conjunction with ICAART 2022, 3-5 February (Online Event) and is available at : http://dx.doi.org/10.5220/0010911100003122

PERMALINK : https://www.eurecom.fr/publication/6806