ThompsonJW032012T.pdf (2.01 MB)
Iris Perturbation Methods for Improved Recognition
thesis
posted on 2012-03-14, 00:00 authored by Joseph William ThompsonPerturbations of software provided circular segmentations are used to generatemultiple probe templates from a single image. The multiple probes are matchedagainst a gallery in order to improve the verification rate of the original algorithm.Using too many of the generated probes will result in greatly increased runningtimes. As a result, various methods of finding and selecting perturbations to beused are empirically examined. Using ROC analysis of the true accept rate (TAR)at a given false accept rate of 0.001, many methods are discovered that performmuch better than the original algorithm, approximate the performance of usingevery perturbation to less than 0.2%, and require between 500 to 1000 times lesstime to verify a single image.
History
Date Modified
2017-06-02Research Director(s)
Patrick FlynnCommittee Members
Karen Hollingsworth Kevin BowyerDegree
- Master of Science in Computer Science and Engineering
Degree Level
- Master's Thesis
Language
- English
Alternate Identifier
etd-03142012-121230Publisher
University of Notre DameProgram Name
- Computer Science and Engineering
Usage metrics
Categories
No categories selectedLicence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC