Open Information System for Minimizing of Iris Recognition Errors Abstract
DOI:
https://doi.org/10.14258/izvasu(2015)1.1-30Keywords:
iris, personal identification, biometrics, information systemAbstract
We present the information system that allows us to minimize errors in the iris recognition by varying the settings of iris recognition algorithms. The information system has a modular design that allows replacement of iris recognition algorithms at any stage for improving system performance and recognition quality. We propose a method for improving the iris detection accuracy by changing parameters of the integro-differential operator used for localization of iris boundaries. It is shown that the application of the integro-differential operator along a certain contour allows us to improve the iris detection accuracy. We demonstrate that changing parameters of the Gabor filter for normalized iris image parameterization also improves the quality of iris recognition. Conducted numerical experiments allow us to select optimal parameters for the Gabor filter. It is shown that a number of shifts in a comparison process of iris images binary codes affects the overall performance and recognition error. Thus, multiple shifts significantly reduce the recognition error due to getting invariance to eye rotation during the iris scanning.
DOI 10.14258/izvasu(2015)1.1-30
Downloads
References
Wayman J. et al. Biometric Systems: Technology, Design and Performance Evaluation. - London, 2005.
2
Iridian Technologies. Historical timeline [Electronic resourse]. URL: www.iridiantech.com/about.php?page=4
3
Третьяков И.Н., Минакова Н.Н. Алгоритм разграничения доступа по радужной оболочке глаза для решения задач контроля доступа к информационным ресурсам // Доклады Томского государственного университета систем управления и радиоэлектроники. - 2010. - №1/1.
4
Петров И.В., Минакова Н.Н. Параметризация структуры радужной оболочки глаза с использованием вейвлет-преобразования // Известия Алтайского гос. ун-та. - 2011. - №1.
5
CASIA. Iris images database [Electronic resourse]. URL: http://biometrics.idealtest.org/dbDetailForUser.do?id=4
6
Proenc,a H., Alexandre L.A. Ubiris: A noisy iris image database[Electronic resourse]. URL: http://iris.di.ubi.pt/
7
Philips J. Ice [Electronic resourse]. URL: http://iris.nist. gov/ice/
8
Libor Masek. Recognition of human iris patterns [Electronic resourse]. URL: http://www.csse.uwa.edu.au/~pk/ studentprojects/libor/
9
Petrovska-Delacretaz D. et al. Guide to Biometric Reference Systems and Performance Evaluation. - London, 2009.
10
Кухарев ГА. Биометрические системы: методы и средства идентификации личности человека. - СПб., 2001.
11
Минакова Н.Н., Петров И.В. Информационная система анализа структуры радужной оболочки глаза // Ползуновский вестник. - 2012. - № 3/2.
12
Daugman J. High confidence visual recognition of persons by a test of statistical independence // IEEE Transactions on Pattern Analysis and Machine Intelligence. - 1993. -Vol. 15, № 11.
Downloads
Issue
Section
License
Izvestiya of Altai State University is a golden publisher, as we allow self-archiving, but most importantly we are fully transparent about your rights.
Authors may present and discuss their findings ahead of publication: at biological or scientific conferences, on preprint servers, in public databases, and in blogs, wikis, tweets, and other informal communication channels.
Izvestiya of Altai State University allows authors to deposit manuscripts (currently under review or those for intended submission to Izvestiya of Altai State University) in non-commercial, pre-print servers such as ArXiv.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License (CC BY 4.0) that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
