Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

A Novel Methodology for the Interoperability Evaluation of An Iris Segmentation Algorithm

Gertsovich, Irina ; Ström Bartunek, Josef ; Håkansson, Lars and Nilsson, Mikael LU (2013) 6th IEEE International conference on Biometrics: Theory, Applications and Systems (BTAS 2013)
Abstract
The performance of an iris recognition system depends

greatly on how well the iris segmentation part of the system

performs its task. The performance of an iris segmenta-

tion algorithm can be evaluated using different criteria and

methods. Some of the methods evaluate the performance of

the segmentation algorithm based on the performance of the

whole iris recognition system. Other methods evaluate the

performance of an iris segmentation subsystem independent

of the performance of the system’s other subsystems. To our

knowledge there do not exist a generally accepted method

or criteria for the evaluation of the standalone iris segmen-

tation... (More)
The performance of an iris recognition system depends

greatly on how well the iris segmentation part of the system

performs its task. The performance of an iris segmenta-

tion algorithm can be evaluated using different criteria and

methods. Some of the methods evaluate the performance of

the segmentation algorithm based on the performance of the

whole iris recognition system. Other methods evaluate the

performance of an iris segmentation subsystem independent

of the performance of the system’s other subsystems. To our

knowledge there do not exist a generally accepted method

or criteria for the evaluation of the standalone iris segmen-

tation subsystem. This paper proposes a novel methodology

to compare the performance of different iris segmentation

algorithms, applied to different image datasets in a consis-

tent way. The methodology employs the F1 score and an empirical cumulative distribution function. The implementation of the F

1 score estimation, adapted to the iris segmentation task is described. Finally the application of the proposed methodology is demonstrated and discussed. (Less)
Please use this url to cite or link to this publication:
author
; ; and
organization
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
subject
host publication
Biometrics: Theory, Applications and Systems (BTAS), 2013 IEEE Sixth International Conference on
editor
Ross, Arun and Kakadiaris, Ioannis A.
pages
6 pages
publisher
IEEE - Institute of Electrical and Electronics Engineers Inc.
conference name
6th IEEE International conference on Biometrics: Theory, Applications and Systems (BTAS 2013)
conference dates
2013-09-29 - 2013-10-02
external identifiers
  • scopus:84893727660
DOI
10.1109/BTAS.2013.6712698
language
English
LU publication?
yes
id
2dcdbfc4-1dc3-4ca9-8903-249ad5d1cd32 (old id 4276201)
date added to LUP
2016-04-04 11:00:24
date last changed
2022-01-29 21:09:24
@inproceedings{2dcdbfc4-1dc3-4ca9-8903-249ad5d1cd32,
  abstract     = {{The performance of an iris recognition system depends<br/><br>
greatly on how well the iris segmentation part of the system<br/><br>
performs its task. The performance of an iris segmenta-<br/><br>
tion algorithm can be evaluated using different criteria and<br/><br>
methods. Some of the methods evaluate the performance of<br/><br>
the segmentation algorithm based on the performance of the<br/><br>
whole iris recognition system. Other methods evaluate the<br/><br>
performance of an iris segmentation subsystem independent<br/><br>
of the performance of the system’s other subsystems. To our<br/><br>
knowledge there do not exist a generally accepted method<br/><br>
or criteria for the evaluation of the standalone iris segmen-<br/><br>
tation subsystem. This paper proposes a novel methodology<br/><br>
to compare the performance of different iris segmentation<br/><br>
algorithms, applied to different image datasets in a consis-<br/><br>
tent way. The methodology employs the F1 score and an empirical cumulative distribution function. The implementation of the F<br/><br>
1 score estimation, adapted to the iris segmentation task is described. Finally the application of the proposed methodology is demonstrated and discussed.}},
  author       = {{Gertsovich, Irina and Ström Bartunek, Josef and Håkansson, Lars and Nilsson, Mikael}},
  booktitle    = {{Biometrics: Theory, Applications and Systems (BTAS), 2013 IEEE Sixth International Conference on}},
  editor       = {{Ross, Arun and Kakadiaris, Ioannis A.}},
  language     = {{eng}},
  publisher    = {{IEEE - Institute of Electrical and Electronics Engineers Inc.}},
  title        = {{A Novel Methodology for the Interoperability Evaluation of An Iris Segmentation Algorithm}},
  url          = {{http://dx.doi.org/10.1109/BTAS.2013.6712698}},
  doi          = {{10.1109/BTAS.2013.6712698}},
  year         = {{2013}},
}