• Login
    View Item 
    •   Shocker Open Access Repository Home
    • Graduate Student Research
    • ETD: Electronic Theses and Dissertations
    • Master's Theses
    • View Item
    •   Shocker Open Access Repository Home
    • Graduate Student Research
    • ETD: Electronic Theses and Dissertations
    • Master's Theses
    • View Item
    JavaScript is disabled for your browser. Some features of this site may not work without it.

    Bias of facial analysis at NIR spectrum

    View/Open
    thesis (1.408Mb)
    Date
    2022-05
    Author
    Neas, Brian
    Advisor
    Rattani, Ajita
    Metadata
    Show full item record
    Abstract
    This paper investigates the effectiveness of using NIR images to mitigate bias in facial recognition and gender classification systems. Two datasets, CASIA-Africa and Notre Dame (ND-VIL) were combined to create a dataset of NIR images that were balanced by race and gender. ResNet-50, SEResNet, LightCNN, and DenseNet-121 were trained on this dataset for facial recognition and gender classification. LightCNN was found to be the most effective model for performing both tasks. An analysis of the genuine and imposter distributions and the FMR-FNMR curves showed that white subjects performed better than black subjects and that male subjects performed slightly better than female subjects, but not in all instances. In gender classification, the best models showed to be slightly biased towards males. NIR images appear to show promise at helping lessen the degree of bias in these systems, and future work with a more consistent quality of images for black and white subjects could lead to a further reduction in bias.
    Description
    Thesis (M.S.)-- Wichita State University, College of Engineering, School of Computing
    URI
    https://soar.wichita.edu/handle/10057/23458
    Collections
    • CE Theses and Dissertations
    • Master's Theses
    • SoC Theses

    Browse

    All of Shocker Open Access RepositoryCommunities & CollectionsBy Issue DateAuthorsTitlesSubjectsBy TypeThis CollectionBy Issue DateAuthorsTitlesSubjectsBy Type

    My Account

    LoginRegister

    Statistics

    Most Popular ItemsStatistics by CountryMost Popular Authors

    DSpace software copyright © 2002-2022  DuraSpace
    DSpace Express is a service operated by 
    Atmire NV