Dissertation/Thesis Abstract

Analysis of facial marks as biometric signatures for forensic facial identification
by Srinivas, Nisha, Ph.D., University of Notre Dame, 2015, 183; 3731722
Abstract (Summary)

Continuing advancements in the field of digital cameras and surveillance imaging devices have led law enforcement and intelligence agencies to use analysis of images and videos for the investigation and prosecution of crime. When determining identity from photographic evidence, forensic analysts perform comparison of visible facial features manually, which is ineffcient.

In this dissertation, we conduct a complete study on the usability of facial marks as biometric signatures to distinguish individuals. We design systems to assist forensic analysts during photographic comparison and systems to highlight the challenges encountered in using facial marks as a biometric modality. We present three different facial mark systems: a manual facial mark system, a multiscale facial mark system in which facial marks are detected automatically, and a semi-automatic facial mark system which integrates human knowledge within the multi-scale facial mark system. We propose to use facial marks to perform pose invariant face recognition.

Experimental results employ a high-resolution time-elapsed dataset acquired at the University of Notre Dame between 2009-2011 and a high resolution identical twins dataset acquired at the Twins Days Festival in Twinsburg, Ohio. The results indicate that the geometric distributions of facial mark patterns can be used to distinguish between individuals.

Indexing (document details)
Advisor: Flynn, Patrick J.
Commitee: Bowyer, Kevin, Riek, Laurel, Thain, Douglas
School: University of Notre Dame
Department: Computer Science and Engineering
School Location: United States -- Indiana
Source: DAI-B 77/03(E), Dissertation Abstracts International
Subjects: Computer Engineering
Keywords: Facial mark systems, Facial recognition, Image analysis, Surveillance imaging
Publication Number: 3731722
ISBN: 978-1-339-18165-3
Copyright © 2020 ProQuest LLC. All rights reserved. Terms and Conditions Privacy Policy Cookie Policy