Optimization of Convolutional Neural Network Structure for Biometric Authentication by Face Geometry

  • Zhengbing Hu
  • Igor Tereykovskiy
  • Yury Zorin
  • Lyudmila Tereykovska
  • Alibiyeva Zhibek
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 754)

Abstract

The article presents development of the methodology of using a convolutional neural network for biometric authentication based on the analysis of the user face geometry. The need to create a method of the structural parameters of convolutional neural network adaptation to the expected conditions of its use in a biometric authentication system is postulated. It is proposed to adapt the convolutional neural network structural parameters based on the maximum similarity to the process of recognizing a human face image by an average user considering peculiar properties of computer input and display. A group of principles for optimization methods is formulated by combining this assumption with the generally accepted concept of a convolutional neural network constructing. The number of convolution layers should be equal to the number of the person image recognition levels by an average user. The number of feature maps in the n-th convolutional layer should be equal to the number of features at the n-th recognition level. The feature map in the n-th layer, corresponding to the j-th recognition feature, is associated only with those feature maps of the previous layer that are used to build the specified figure. The size of the convolution kernel for the n-th convolutional layer should be equal to the size of the recognizable feature on the n-th hierarchical level. Based on these principles, a method of the structural parameters optimization of a convolutional neural network has been developed. Advisability of these principles use has been proved experimentally.

Keywords

Biometric authentication Neural network model Convolutional neural network Optimization Recognition Facial geometry 

Notes

Acknowledgment

This scientific work was financially supported by self-determined research funds of CCNU from the colleges’ basic research and operation of MOE (CCNU16A02015).

References

  1. 1.
    Arsentyev, D.A., Biryukova, T.S.: Method of flexible comparison on graphs as algorithm of images recognition. Bull. Ivan Fedorov MGUP 6, 74–75 (2015). (in Russian)Google Scholar
  2. 2.
    Bryliuk, D., Starovoitov, V.: Application of recirculation neural network and principal component analysis for face recognition. In: The 2nd International Conference on Neural Networks and Artificial Intelligence, BSUIR, Minsk, pp. 136–142 (2001)Google Scholar
  3. 3.
    Chirchi, V.R.E., Waghmare, L.M.: Iris biometric authentication used for security systems. Int. J. Image Graph. Sig. Process. (IJIGSP) 6(9), 54–60 (2014).  https://doi.org/10.5815/ijigsp.2014.09.07CrossRefGoogle Scholar
  4. 4.
    Connaughton, R., Bowyer, K.W., Flynn, P.J.: Fusion of face and iris biometrics. In: Handbook of Iris Recognition, pp. 219–237. Springer, London (2013)Google Scholar
  5. 5.
    Dyomin, A.A.: Adaptive processing of the calligraphic information presented in the form of hand-written symbols. Ph.D. dissertation, Moscow, p. 182 (2014). (in Russian)Google Scholar
  6. 6.
    Fedotov, D.V., Popov, V.A.: Optimisation of convolutional neural network structure with self-configuring evolutionary algorithm in one identification problem. Vestnik SibGAU 16(4), 857–862 (2013). (in Russian)Google Scholar
  7. 7.
    Hurshudov, A.A.: Development of the system of recognition of visual images in data stream. Ph.D. dissertation, Krasnodar, p. 130 (2015). (in Russian)Google Scholar
  8. 8.
    Ibragimov, V.V., Arsentyev, D.A.: Algorithms and methods of person recognition in modern information technologies. Bull. Ivan Fedorov MGUP 1, 37–41 (2015). (in Russian)Google Scholar
  9. 9.
    Korchenko, A., Tereykovsky, I., Karpinsky, N., Tynymbayev, S.: Neural network models, methods and means of safety parameters assessment of the Internet focused information systems. In: Our Format, p. 275 (2016). (in Russian)Google Scholar
  10. 10.
    Narendira Kumar, V.K., Srinivasan, B.: New biometric approaches for improved person identification using facial detection. Int. J. Image Graph. Sig. Process. (IJIGSP) 4(8), 43–49 (2012).  https://doi.org/10.5815/ijigsp.2012.08.06CrossRefGoogle Scholar
  11. 11.
    Zoubida, L., Adjoudj, R.: Integrating face and the both irises for personal authentication. Int. J. Intell. Syst. Appl. (IJISA) 9(3), 8–17 (2017).  https://doi.org/10.5815/ijisa.2017.03.02CrossRefGoogle Scholar
  12. 12.
    Mishchenko, V.A.: Algorithm of recognition of graphic images. Bull. Voronezh State Tech. Univ. 5(12), 103–105 (2009). (in Russian)Google Scholar
  13. 13.
    Ross, A., Jain, A.K.: Fusion techniques in multibiometric systems. In: Hammound, R.I., Abidi, B.R., Abidi, M.A. (eds.) Face Biometrics for Personal Identification, pp. 185–212. Springer, Heidelberg (2007)Google Scholar
  14. 14.
    Soldatova, O.P., Garshin, A.A.: Application of convolutional neural network for recognition of hand-written figures. Comput. Opt. 2, 252–258 (2010). (in Russian)Google Scholar
  15. 15.
    Hu, Z., Tereykovskiy, I.A., Tereykovska, L.O., Pogorelov, V.V.: Determination of structural parameters of multilayer perceptron designed to estimate parameters of technical systems. Int. J. Intell. Syst. Appl. (IJISA) 9(10), 57–62 (2017).  https://doi.org/10.5815/ijisa.2017.10.07CrossRefGoogle Scholar
  16. 16.
    Hu, Z., Gnatyuk, S., Koval, O., Gnatyuk, V., Bondarovets, S.: Anomaly detection system in secure cloud computing environment. International Journal of Computer Network and Information Security (IJCNIS) 9(4), 10–21 (2017).  https://doi.org/10.5815/ijcnis.2017.04.02CrossRefGoogle Scholar
  17. 17.
    Hu, Z., Gnatyuk, V., Sydorenko, V., Odarchenko, R., Gnatyuk, S.: Method for cyberincidents network-centric monitoring in critical information infrastructure. Int. J. Comput. Netw. Inf. Secur. (IJCNIS) 9(6), 30–43 (2017).  https://doi.org/10.5815/ijcnis.2017.06.04CrossRefGoogle Scholar
  18. 18.
    Hu, Z., Dychka, I.A., Mykola, O., Andrii, B.: The analysis and investigation of multiplicative inverse searching methods in the ring of integers modulo M. Int. J. Intell. Syst. Appl. (IJISA) 8(11), 9–18 (2016).  https://doi.org/10.5815/ijcnis.2017.06.04CrossRefGoogle Scholar
  19. 19.
    Umyarov, N.H., Yu, K.G., Fedyaev, O.I.: A software model of convolutional neural network. Information management systems and computer monitoring. In: Proceedings of III Ukrainian Scientific Technical Conference of Students, Graduate Students that Young Scientists, 16–19 April 2012, Donetsk, pp. 343–347 (2012). (in Russian) Google Scholar

Copyright information

© Springer International Publishing AG, part of Springer Nature 2019

Authors and Affiliations

  1. 1.School of Educational Information TechnologyCentral China Normal UniversityWuhanChina
  2. 2.National Technical University of Ukraine “Igor Sikorsky Kyiv Polytechnic Institute”KyivUkraine
  3. 3.Kyiv National University of Construction and ArchitectureKyivUkraine
  4. 4.Kazakh National Research Technical University named after K.I. SatpayevAlmatyRepublic of Kazakhstan

Personalised recommendations