NDLTD Global ETD Search
  • Refine Query
  • Source
  • Publication year
  • to
  • Language
  • 1
  • Tagged with
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • About
  • The Global ETD Search service is a free service for researchers to find electronic theses and dissertations. This service is provided by the Networked Digital Library of Theses and Dissertations.
    Our metadata is collected from universities around the world. If you manage a university/consortium/country archive and want to be added, details can be found on the NDLTD website.

Search results

Showing 1 to 1 of 1 (0.143 seconds)

Spelling suggestions: "subject:"AI fairness anda data augmentation"" "subject:"AI fairness anda data daugmentation""

1

Enhancing Fairness in Facial Recognition: Balancing Datasets and Leveraging AI-Generated Imagery for Bias Mitigation : A Study on Mitigating Ethnic and Gender Bias in Public Surveillance Systems

Abbas, Rashad, Tesfagiorgish, William Issac January 2024 (has links)
Facial recognition technology has become a ubiquitous tool in security and personal identification. However, the rise of this technology has been accompanied by concerns over inherent biases, particularly regarding ethnic and gender. This thesis examines the extent of these biases by focusing on the influence of dataset imbalances in facial recognition algorithms. We employ a structured methodological approach that integrates AI-generated images to enhance dataset diversity, with the intent to balance representation across ethnics and genders. Using the ResNet and Vgg model, we conducted a series of controlled experiments that compare the performance impacts of balanced versus imbalanced datasets. Our analysis includes the use of confusion matrices and accuracy, precision, recall and F1-score metrics to critically assess the model’s performance. The results demonstrate how tailored augmentation of training datasets can mitigate bias, leading to more equitable outcomes in facial recognition technology. We present our findings with the aim of contributing to the ongoing dialogue regarding AI fairness and propose a framework for future research in the field.
Facial Recognition Technology
Algorithmic Bias
Dataset Imbalance
ethnic and Gender Representation
AI-Generated Images
ResNet Model
Vgg model
Model Performance Evaluation
Confusion Matrices
AI Fairness and Data Augmentation
Engineering and Technology
Teknik och teknologier
Computer Sciences
Datavetenskap (datalogi)
Computer and Information Sciences
Data- och informationsvetenskap

Page generated in 0.1472 seconds