2026-09-19T03:46:58Zhttps://dspace.mit.edu/server/oai/requestoai:dspace.mit.edu:1721.1/1473132023-01-20T03:11:22Zcom_1721.1_7582com_1721.1_7581col_1721.1_131023
Sinha, Pawan
Keane, Kyle
Verma, Ashika
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
2023-01-19T18:44:50Z
2023-01-19T18:44:50Z
2022-09
2022-09-16T20:24:09.975Z
https://hdl.handle.net/1721.1/147313
Face recognition is widely acknowledged to be a very complex visual task for both humans and computers. Previous studies which analyze robustness of facial recognition systems have revealed that the ability to recognize faces becomes worse as the blur levels of face images increases, and that naturalistic color is important for facial recognition at high blur levels. Additionally, previous studies of current state of the art face recognition technologies have found bias in face recognition amongst different races, resulting in a worse recognition performance for people of color. In this study, we evaluate the performance and robustness of a current state-of-the-art facial recognition neural network architecture (ResNet-101) trained on an augmented facial identity dataset (Augmented Casia Webface) and perform a thorough comparison between White, Black and East Asian identities. We created a full-color, a grayscale and many hue-shifted datasets and then Gaussian blurred each dataset at different intensities and compared how AI systems perform relative to humans and amongst the different races.
M.Eng.
Massachusetts Institute of Technology
In Copyright - Educational Use Permitted
Copyright MIT
http://rightsstatements.org/page/InC-EDU/1.0/
Transformation Tolerance and Demographic Robustness of Machine-based Face Recognition Systems
Thesis
application/pdf
Master
Master of Engineering in Electrical Engineering and Computer Science
Publication
unknown
unknown
<Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="c9efb54b-ff6a-436d-b474-8a8fbc40db80">
<Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843</Type>
<Title>Transformation Tolerance and Demographic Robustness of Machine-based Face Recognition Systems</Title>
<PublishedIn>
<Publication>
</Publication>
</PublishedIn>
<PublicationDate>2022-09</PublicationDate>
<Authors>
<Author>
<DisplayName>Verma, Ashika</DisplayName>
<Affiliation>
<OrgUnit>
</OrgUnit>
</Affiliation>
</Author>
</Authors>
<Editors>
</Editors>
<Publishers>
<Publisher>
<DisplayName>Massachusetts Institute of Technology</DisplayName>
<OrgUnit />
</Publisher>
</Publishers>
<License>http://rightsstatements.org/page/InC-EDU/1.0/</License>
<Abstract>Face recognition is widely acknowledged to be a very complex visual task for both humans and computers. Previous studies which analyze robustness of facial recognition systems have revealed that the ability to recognize faces becomes worse as the blur levels of face images increases, and that naturalistic color is important for facial recognition at high blur levels. Additionally, previous studies of current state of the art face recognition technologies have found bias in face recognition amongst different races, resulting in a worse recognition performance for people of color. In this study, we evaluate the performance and robustness of a current state-of-the-art facial recognition neural network architecture (ResNet-101) trained on an augmented facial identity dataset (Augmented Casia Webface) and perform a thorough comparison between White, Black and East Asian identities. We created a full-color, a grayscale and many hue-shifted datasets and then Gaussian blurred each dataset at different intensities and compared how AI systems perform relative to humans and amongst the different races.</Abstract>
<Access xmlns="http://purl.org/coar/access_right"
>
</Access>
</Publication>