Optimization of Deep Neural Network for Recognition with Human Iris Biometric Measure

  • Fernando GaxiolaEmail author
  • Patricia Melin
  • Fevrier Valdez
  • Juan R. Castro
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 648)


In this paper an optimization approach with genetic algorithms for a deep neural network is applied. We optimize some parameters for the deep neural network that allowed optimize the results of the recognition of persons, like the number of neurons in the first and second hidden layer, and others. We work with the human iris like the biometric measure for the recognition of persons. Before give like input the human iris images to the deep neural network, pre-processing methods for eliminate the noise around the iris are applied. The proposed optimization allowed to the deep neural network increase the performance of recognition.


Genetic algorithm Deep neural network Person recognition Human iris 


  1. 1.
    Yan, F., Lin, Z., Wang, X., Azarmi, F., Sobolev, K.: Evaluation and prediction of bond strength of GFRP-bar reinforced concrete using artificial neural network optimized with genetic algorithm. Compos. Struct. 161, 441–452 (2017)CrossRefGoogle Scholar
  2. 2.
    Hidalgo, D., Melin, P., Castro, J.R.: Non-singleton interval type-2 fuzzy systems as integration methods in modular neural networks used genetic algorithms to design. Stud. Comput. Intell. 667, 821–838 (2016)Google Scholar
  3. 3.
    Gaxiola, F., Melin, P., Valdez, F., Castro, J.R.: Optimization of type-2 and type-1 fuzzy integrator to ensemble neural network with fuzzy weights adjustment. Stud. Comput. Intell. 667, 39–61 (2016)Google Scholar
  4. 4.
    Hore, S., Chatterjee, S., Santhi, V., Dey, N., Ashour, A., Balas, V.E., Shi, F.: Indian sign language recognition using optimized neural networks. In: Proceedings of 2015 International Conference on Information Technology and Intelligent Transportation Systems (ITITS 2015), vol. 2, pp. 553–563 (2016)Google Scholar
  5. 5.
    Zameer, A., Arshad, J., Khan, A., Raja, M.A.Z.: Intelligent and robust prediction of short term wind power using genetic programming based ensemble of neural networks. Energy Convers. Manag. 134, 361–372 (2017)CrossRefGoogle Scholar
  6. 6.
    Sonule, P.M., Shetty, B.S.: An enhanced fuzzy min–max neural network with ant colony optimization based-rule-extractor for decision making. Neurocomputing 239, 204–213 (2017)CrossRefGoogle Scholar
  7. 7.
    Song, Q., Zheng, Y.J., Xue, Y., Sheng, W.G., Zhao, M.R.: An evolutionary deep neural network for predicting morbidity of gastrointestinal infections by food contamination. Neurocomputing 226, 16–22 (2017)CrossRefGoogle Scholar
  8. 8.
    Du, J., Xu, Y.: Hierarchical deep neural network for multivariate regression. Pattern Recogn. 63, 149–157 (2017)CrossRefGoogle Scholar
  9. 9.
    Sanchez, D., Melin, P., Carpio, J., Puga, H.: Comparison of optimization techniques for modular neural networks applied to human recognition. Stud. Comput. Intell. 667, 225–241 (2016)Google Scholar
  10. 10.
    Daugman, J.: Statistical richness of visual phase information: update on recognizing persons by iris patterns. Int. J. Comput. Vis. 45(1), 25–38 (2001)CrossRefzbMATHGoogle Scholar
  11. 11.
    Risk, M., Farag, H., Said, L.: Neural network classification for iris recognition using both particle swarm optimization and gravitational search algorithm. In: 2016 World Symposium on Computer Applications & Research (WSCAR), pp. 12–17 (2016)Google Scholar
  12. 12.
    Cruz, F.R.G., Hortinela, C.C., Redosendo, B.E., Asuncion, B.K., Leoncio, C.J., Linsangan, N.B., Chung, W.: Iris recognition using Daugman algorithm on Raspberry Pi. In: 2016 IEEE Region 10 Conference (TENCON), pp. 2126–2129 (2016)Google Scholar
  13. 13.
    Birajadar, P., Shirvalkar P., Gupta S., Patidar V., Sharma U., Naik A., Gadre V.: A novel iris recognition technique using monogenic wavelet phase encoding. In: 2016 International Conference on Signal and Information Processing (IConSIP), pp. 1–6 (2016)Google Scholar
  14. 14.
    Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: Conference on ICLR 2015, pp. 1–13 (2015)Google Scholar
  15. 15.
    Rhee, S.M., Yoo, B., Han, J.J., Hwang, W.: Deep neural network using color and synthesized three-dimensional shape for face recognition. J. Electron. Imaging 26(2), 020502 (2017)CrossRefGoogle Scholar
  16. 16.
    Hinton, G., Deng, L., Yu, D., Dahl, G., Mohamed, A., Jaitly, N., Senior, A., Vanhoucke, V., Nguyen, P., Sainath, T., Kingsbury, B.: Deep neural networks for acoustic modeling in speech recognition: the shared views of four research groups. IEEE Sig. Process. Mag. 29(6), 82–97 (2012)CrossRefGoogle Scholar
  17. 17.
    Masek, L., Kovesi, P.: MATLAB source code for a biometric identification system based on iris patterns. The School of Computer Science and Software Engineering the University of Western Australia (2003)Google Scholar

Copyright information

© Springer International Publishing AG 2018

Authors and Affiliations

  • Fernando Gaxiola
    • 1
    Email author
  • Patricia Melin
    • 2
  • Fevrier Valdez
    • 2
  • Juan R. Castro
    • 3
  1. 1.Autonomous University of ChihuahuaChihuahuaMexico
  2. 2.Tijuana Institute of TechnologyTijuanaMexico
  3. 3.Autonomous University of Baja CaliforniaTijuanaMexico

Personalised recommendations