Experimental Evaluation of the Effect of Reversible Watermarking on Iris Recognition

Research output: Contribution to conferenceOther

Abstract

Fragile watermarking has been proposed as a means of
adding additional security or functionality to biometric sys-
tems, particularly for authentication and tamper detection.
In this paper we describe an experimental study investigat-
ing the effect of watermarking iris images with a particular
class of fragile algorithm, reversible watermarking, on the
ability to correctly perform iris recognition. We investigate
two scenarios, matching watermarked images to unmodi-
fied images, and matching watermarked images to water-
marked images. We found that the payload capacity and
watermarking scheme chosen can have a significant effect
on the performance seen. At high embedding rates most al-
gorithms cause significant reduction in recognition perfor-
mance. However, in many cases, for low embedding rates,
an increase in recognition performance was found.
Original languageEnglish
Number of pages6
Publication statusUnpublished - 2012
EventThe IEEE Fifth International Conference on Biometrics: Theory, Applications and Systems (BTAS 2012) - Washington, DC, United States
Duration: 23 Sep 201227 Sep 2012

Conference

ConferenceThe IEEE Fifth International Conference on Biometrics: Theory, Applications and Systems (BTAS 2012)
CountryUnited States
CityWashington, DC
Period23/09/1227/09/12

Fingerprint

Image matching
Watermarking
Image watermarking
Biometrics
Authentication
Water

Cite this

Lock, A. D., & Allen, A. R. (2012). Experimental Evaluation of the Effect of Reversible Watermarking on Iris Recognition. The IEEE Fifth International Conference on Biometrics: Theory, Applications and Systems (BTAS 2012), Washington, DC, United States.

Experimental Evaluation of the Effect of Reversible Watermarking on Iris Recognition. / Lock, A D; Allen, Alastair Robert.

2012. The IEEE Fifth International Conference on Biometrics: Theory, Applications and Systems (BTAS 2012), Washington, DC, United States.

Research output: Contribution to conferenceOther

Lock, AD & Allen, AR 2012, 'Experimental Evaluation of the Effect of Reversible Watermarking on Iris Recognition' The IEEE Fifth International Conference on Biometrics: Theory, Applications and Systems (BTAS 2012), Washington, DC, United States, 23/09/12 - 27/09/12, .
Lock AD, Allen AR. Experimental Evaluation of the Effect of Reversible Watermarking on Iris Recognition. 2012. The IEEE Fifth International Conference on Biometrics: Theory, Applications and Systems (BTAS 2012), Washington, DC, United States.
Lock, A D ; Allen, Alastair Robert. / Experimental Evaluation of the Effect of Reversible Watermarking on Iris Recognition. The IEEE Fifth International Conference on Biometrics: Theory, Applications and Systems (BTAS 2012), Washington, DC, United States.6 p.
@conference{25b1310c2d9044f5b101f216deef10ac,
title = "Experimental Evaluation of the Effect of Reversible Watermarking on Iris Recognition",
abstract = "Fragile watermarking has been proposed as a means ofadding additional security or functionality to biometric sys-tems, particularly for authentication and tamper detection.In this paper we describe an experimental study investigat-ing the effect of watermarking iris images with a particularclass of fragile algorithm, reversible watermarking, on theability to correctly perform iris recognition. We investigatetwo scenarios, matching watermarked images to unmodi-fied images, and matching watermarked images to water-marked images. We found that the payload capacity andwatermarking scheme chosen can have a significant effecton the performance seen. At high embedding rates most al-gorithms cause significant reduction in recognition perfor-mance. However, in many cases, for low embedding rates,an increase in recognition performance was found.",
author = "Lock, {A D} and Allen, {Alastair Robert}",
year = "2012",
language = "English",
note = "The IEEE Fifth International Conference on Biometrics: Theory, Applications and Systems (BTAS 2012) ; Conference date: 23-09-2012 Through 27-09-2012",

}

TY - CONF

T1 - Experimental Evaluation of the Effect of Reversible Watermarking on Iris Recognition

AU - Lock, A D

AU - Allen, Alastair Robert

PY - 2012

Y1 - 2012

N2 - Fragile watermarking has been proposed as a means ofadding additional security or functionality to biometric sys-tems, particularly for authentication and tamper detection.In this paper we describe an experimental study investigat-ing the effect of watermarking iris images with a particularclass of fragile algorithm, reversible watermarking, on theability to correctly perform iris recognition. We investigatetwo scenarios, matching watermarked images to unmodi-fied images, and matching watermarked images to water-marked images. We found that the payload capacity andwatermarking scheme chosen can have a significant effecton the performance seen. At high embedding rates most al-gorithms cause significant reduction in recognition perfor-mance. However, in many cases, for low embedding rates,an increase in recognition performance was found.

AB - Fragile watermarking has been proposed as a means ofadding additional security or functionality to biometric sys-tems, particularly for authentication and tamper detection.In this paper we describe an experimental study investigat-ing the effect of watermarking iris images with a particularclass of fragile algorithm, reversible watermarking, on theability to correctly perform iris recognition. We investigatetwo scenarios, matching watermarked images to unmodi-fied images, and matching watermarked images to water-marked images. We found that the payload capacity andwatermarking scheme chosen can have a significant effecton the performance seen. At high embedding rates most al-gorithms cause significant reduction in recognition perfor-mance. However, in many cases, for low embedding rates,an increase in recognition performance was found.

M3 - Other

ER -