Author ORCID Identifier

https://orcid.org/0000-0002-7853-6935

Semester

Summer

Date of Graduation

2023

Document Type

Dissertation

Degree Type

PhD

College

Statler College of Engineering and Mineral Resources

Department

Lane Department of Computer Science and Electrical Engineering

Committee Chair

Nasser Nasrabadi

Committee Member

Matthew Valenti

Committee Member

Jeremy Dawson

Committee Member

Omid Dehzangi

Committee Member

Piyush Mehta

Abstract

Morphed face images are maliciously used by criminals to circumvent the official process for receiving a passport where a look-alike accomplice embarks on requesting a passport. Morphed images are either synthesized by alpha-blending or generative networks such as Generative Adversarial Networks (GAN). Detecting morphed images is one of the fundamental problems associated with border control scenarios. Deep Neural Networks (DNN) have emerged as a promising solution for a myriad of applications such as face recognition, face verification, fake image detection, and so forth. The Biometrics communities have leveraged DNN to tackle fundamental problems such as morphed face detection. In this dissertation, we delve into data-driven morph detection which is of great significance in terms of national security.

We propose several wavelet-based face morph detection schemes which employ some of the computer vision algorithms such as image wavelet analysis, group sparsity, feature selection, and the visual attention mechanisms. Wavelet decomposition enables us to leverage the fine-grained frequency content of an image to boost localizing manipulated areas in an image. Our methodologies are as follows: (1) entropy-based single morph detection, (2) entropy-based differential morph detection, (3) morph detection using group sparsity, and (4) Attention aware morph detection. In the first methodology, we harness mismatches between the entropy distribution of wavelet subbands corresponding to a pair of real and morph images to find a subset of most discriminative wavelet subbands which leads to an increase of morph detection accuracy. As the second methodology, we adopt entropy-based subband selection to tackle differential morph detection. In the third methodology, group sparsity is leveraged for subband selection. In other words, adding a group sparsity constraint to the loss function of our DNN leads to an implicit subband selection. Our fourth methodology consists of different types of visual attention mechanisms such as convolutional block attention modules and self-attention resulting in boosting morph detection accuracy.

We demonstrate efficiency of our proposed algorithms through several morph datasets via extensive evaluations as well as visualization methodologies.

Download

Share

COinS