The problem of pattern recognition dimensionality in biometric authentication systems

Authors

  • Жулдыз Алимсеитова Satpayev University
  • Нургуль Сейлова Satpayev University
  • Сергей Александрович Гнатюк National Aviation University

DOI:

https://doi.org/10.18372/2410-7840.19.12219

Keywords:

biometric image, artificial neural network, neural network Converter, the dimensionality of the task of transformation, correlation, space of distance of the Hamming

Abstract

In biometric authentication systems, the process of prov-ing and verifying the authenticity of a user-claimed name through the user's presentation of his biometric image is performed and by converting this image in accordance with a predefined authentication protocol. An important issue remains the transformation of biometric data into code. The paper discusses the two most well-known conversion technology of biometrics in the code, the scheme of con-version of biometric parameters in the code key. It is shown that one of the main reasons for the difficulties of biometric authentication is the high dimensionality of the problem. To solve this problem, there are artificial neural networks or "fuzzy extractors". Of the many existing learn-ing algorithms of neural networks selected algorithm for automatic training of large artificial neural networks. Shows the use of entropy device to reduce the dimension of the problem of converting the biometrics-code. To reduce the volume of calculations made the transition to the Ham-ming distances.

Author Biographies

Жулдыз Алимсеитова, Satpayev University

lecturer of Academic Department «Information security» at Satpayev University

Нургуль Сейлова, Satpayev University

PhD in Eng, Head of Academic Department «Information security» at Satpayev University

Сергей Александрович Гнатюк, National Aviation University

PhD in Eng, Associate Professor of IT-Security Academic Department, National Aviation University

References

A. Arakala, J. Jeffers, K. J. Horadam, "Fuzzy Extrac-tors for Minutiae-Based Fingerprint Authentication", Advances in Biometrics (LNCS 4642), Springer, pp. 760-769, 2007.

А. Чморра, "Маскировка ключа с помощью биометрии", Проблемы передачи информации, № 2(47), С. 128-143, 2011.

Б. Ахметов, А. Иванов, А. Малыгин, В. Фунтиков, Основы биометрической аутентификации личности, Алматы: КазНТУ, 2014.

ГОСТ Р 52633.5–2011, «Защита информации. Техника защиты информации. Автоматическое обучение нейросетевых преобразователей биометрия-код доступа», М.: Стандартинформ, 2012.

ГОСТ Р 52633.0-2006, Защита информации. Техника защиты информации. Требования к средствам высоконадежной биометрической аутентификации. М.: Стандартинформ, 2007.

Б. Ахметов, О. Захаров, Т. Картбаев, А. Малыгин, А. Иванов, И. Огнев, "Метод оценки вероятностей появления ошибок нейросетевых преобразователей биометрия-код, использующий очень малые тестовые выборки", Вестник КазНТУ имени К.И. Сатпаева, 2013, №3(97), С. 279-283.

А. Иванов, Б. Ахметов, А. Безяев, К. Перфилов, Ж. Алимсеитова, "Вычисление энтропии слабо коррелированных и сильно коррелированных длинных биометрических кодов на малых тестовых выборках", Вестник НАН РК, 2015, №3, С. 64-70.

Б. Ахметов, А. Иванов, Т. Картбаев, Д. Надеев, А. Малыгин, И. Огнев, "Энтропийно-корреляционный подход к расчету вероятности совместного появления большого числа зависимых событий", Вестник КБТУ, 2013, №2(25), С. 54-58.

А. Малыгин, Б. Ахметов, В. Волчихин, И. Урнев, "Учет влияния корреляционных связей на результаты тестирования преобразователей биометрия-код", Информационные и телекоммуникационные технологии: образование, наука, практика: Сборник трудов Международной научно-практической конференции, Алма-ты: КазНТУ, 2012, С. 34–37.

Downloads

Published

2017-12-11

Issue

Vol. 19 No. 4 (2017)

Section

Articles

License

Authors who publish with this journal agree to the following terms:

  1. Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.

  2. 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.

  3. 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).