Improving Iris Recognition through New Target Vectors in MLP Artificial Neural Networks

  • José Ricardo Gonçalves Manzan
  • Shigueo Nomura
  • Keiji Yamanaka
  • Milena Bueno Pereira Carneiro
  • Antônio C. Paschoarelli Veiga
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7477)


This paper compares the performance of multilayer perceptron (MLP) networks trained with conventional bipolar target vectors (CBVs) and orthogonal bipolar new target vectors (OBVs) for biometric pattern recognition. The experimental analysis consisted of using biometric patterns from CASIA Iris Image Database developed by Chinese Academy of Sciences - Institute of Automation. The experiments were performed in order to obtain the best recognition rates, leading to the comparison of results from both conventional and new target vectors. The experimental results have shown that MLPs trained with OBVs can better recognize the patterns of iris images than MLPs trained with CBVs.


Biometric pattern iris image conventional bipolar vector multilayer perceptron orthogonal bipolar vector pattern recognition target vector 


  1. 1.
    Wang, X., Chang, C., Du, F.: Achieving a More Robust Neural Network Model for Control of a MR Damper by Signal Sensitivity Analysis. Neu. Comp. & App. 13, 330–338 (2002)CrossRefGoogle Scholar
  2. 2.
    Costa, M.A., Braga, A.P., Menezes, B.R.: Improving Neural Networks Generalization With New Constructive and Pruning Methods. J. Int. & Fuzzy Syst. 13, 75–83 (2003)zbMATHGoogle Scholar
  3. 3.
    Lee, C.M., Yang, S.S., Ho, C.L.: Modified Back-propagation Algorithm Applied to Decision-feedback Equalization. IEE Proceedings - Vis., Ima. & Sig. Proc. 153, 805–809 (2006)CrossRefGoogle Scholar
  4. 4.
    Kim, D.: Improving Prediction Performance of Neural Networks in Pattern Classification. Int. J. Comp. Math. 82(4), 391–399 (2005)zbMATHCrossRefGoogle Scholar
  5. 5.
    Chen, L., Pung, H.K.: Convergence Analysis of Convex Incremental Neural Networks. Annals of Mathematics and Artificial Intelligence 52, 67–80 (2008)MathSciNetzbMATHCrossRefGoogle Scholar
  6. 6.
    Browne, A.: Neural Network Analysis, Architetures, and Applications. Institute of Physics Pub., Philadelphia (1997)Google Scholar
  7. 7.
    Nomura, S., Yamanaka, K., Katai, O., Kawakami, H., Shiose, T.: Improving MLP Learning Via Orthogonal Bipolar Target Vectors. J. Adv. Comp. Int. and Int. Inf. 9, 580–589 (2005)Google Scholar
  8. 8.
    Nomura, S., Yamanaka, K., Katai, O., Kawakami, H., Shiose, T.: A New Approach to Improving Math Performance of Artificial Neural Networks (in Portuguese). In: VIII Brazilian Symposium on Neural Networks, São Luís (2004)Google Scholar
  9. 9.
    Manzan, J.R.G., Yamanaka, K., Nomura, S.: Improvement in Perfomance of MLP Using New Target Vectors (in Portuguese). In: X Brazilian Congress on Computational Intelligence, Fortaleza (2011)Google Scholar
  10. 10.
    Nomura, S., Manzan, J.R.G., Yamanaka, K.: An Experimentation With Improved Target Vectors for MLP in Classifying Degraded Patterns. Learning and Nonlinear Models 8(4), 240–252 (2010)Google Scholar
  11. 11.
    Cooper, L.N.: A Possible Organization of Animal Memory and Learning. In: Lundquist, B., Lundquist, S. (eds.) Nobel Symposium on Collective Propertiers of Physical Systems, Sweden, pp. 62–84 (1973)Google Scholar
  12. 12.
    Duda, R.O., Hart, P.E.: Pattern Classification and Scene Analysis. Wiley, New York (1973)zbMATHGoogle Scholar
  13. 13.
    Fausset, L.: Fundamentals of Neural Networks: Architecture, Algorithms, and Applications. Prentice-Hall (1994)Google Scholar
  14. 14.
    Chinese Academy of Sciences - Institute of Automation, Database of 756 Greyscale Eye Images,
  15. 15.
    Daugman, J.: High Confidence Visual Recognition of Person by a Test of Statistical Independence. IEEE Transactions on Pattern Analysis and Machine Intelligence 15(11), 1148–1161 (1993)CrossRefGoogle Scholar
  16. 16.
    Negin, M., Chmielewski Jr., T.A., Salganicoff, M., von Seelen, U.M., Venetainer, P.L., Zhang, G.G.: An Iris Biometric System for Public and Personal Use. IEEE Computer Society 33, 70–75 (2000)CrossRefGoogle Scholar
  17. 17.
    Carneiro, M.B.P., Veiga, A.C.P.: Application of Genetic Algorithms to Improve the Realiability of An Iris Recognition System. In: IEEE Workshop on Machine Learning for Signal Processing, Mystic, pp. 159–164 (2005)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • José Ricardo Gonçalves Manzan
    • 1
  • Shigueo Nomura
    • 1
  • Keiji Yamanaka
    • 1
  • Milena Bueno Pereira Carneiro
    • 1
  • Antônio C. Paschoarelli Veiga
    • 1
  1. 1.Faculty of Electrical EngineeringFederal University of UberlândiaUberlândiaBrasil

Personalised recommendations