Show simple item record

dc.contributor.advisorRattani, Ajita
dc.contributor.authorNeas, Brian
dc.descriptionThesis (M.S.)-- Wichita State University, College of Engineering, School of Computing
dc.description.abstractThis 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.
dc.format.extentix, 31 pages
dc.publisherWichita State University
dc.rights© Copyright 2022 by Brian Neas All Rights Reserved
dc.subject.lcshElectronic dissertations
dc.titleBias of facial analysis at NIR spectrum

Files in this item


This item appears in the following Collection(s)

  • CE Theses and Dissertations
    Doctoral and Master's theses authored by the College of Engineering graduate students
  • Master's Theses
    This collection includes Master's theses completed at the Wichita State University Graduate School (Fall 2005 -- current) as well as selected historical theses.
  • SoC Theses
    The School of Computing Master's theses

Show simple item record