A Novel Methodology for the Interoperability Evaluation of An Iris Segmentation Algorithm
(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:
https://lup.lub.lu.se/record/4276201
- author
- Gertsovich, Irina ; Ström Bartunek, Josef ; Håkansson, Lars and Nilsson, Mikael LU
- organization
- publishing date
- 2013
- 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}}, }