Theses and Dissertations
Date of Award
8-2023
Document Type
Thesis
Degree Name
Master of Science (MS)
Department
Computer Science
First Advisor
Emmett Tomai
Second Advisor
Bin Fu
Third Advisor
Zhixiang Chen
Abstract
In the past few years, biometric identification systems have become popular for personal, national, and global security. In addition to other biometric modalities, facial and fingerprint recognition have gained popularity due to their uniqueness, stability, convenience, and cost-effectiveness compared to other biometric modalities. However, the evolution of fake biometrics, such as printed materials, 2D or 3D faces, makeup, and cosmetics, has brought new challenges. As a result of these modifications, several facial and fingerprint Presentation Attack Detection methods have been proposed to distinguish between live and spoof faces or fingerprints. Federated learning can play a significant role in this problem due to its distributed learning setting and privacy-preserving advantages. This work proposes a hybrid ResNet50-SVM based federated learning model for facial Presentation Attack Detection utilizing Local Binary Pattern (LBP), or Gabor filter-based extracted image features. For fingerprint Presentation Attack Detection (PAD), this work proposes a hybrid CNN-SVM based federated learning model utilizing Local Binary Pattern (LBP), or Histograms of Oriented Gradient (HOG)-based extracted image features.
Recommended Citation
Sarwar, S M, "FedBiometric: Image Features Based Biometric Presentation Attack Detection Using Hybrid CNNs-SVM in Federated Learning" (2023). Theses and Dissertations. 1403.
https://scholarworks.utrgv.edu/etd/1403
Comments
Copyright 2023 S M Sarwar. All Rights Reserved.
https://go.openathens.net/redirector/utrgv.edu?url=https://www.proquest.com/dissertations-theses/fedbiometric-image-features-based-biometric/docview/2862098819/se-2?accountid=7119