Development of modular neural networks with fuzzy logic response integration for signature recognition

  • Mónica Beltrán
  • Patricia Melin
  • Leonardo Trujillo
Original Article


This paper describes a modular neural network (MNN) for the problem of signature recognition. Currently, biometric identification has gained a great deal of research interest within the pattern recognition community. For instance, many attempts have been made in order to automate the process of identifying a person’s handwritten signature, however this problem has proven to be a very difficult task. In this work, we propose an MNN that has three separate modules, each using different image features as input, these are: edges, wavelet coefficients, and the Hough transform matrix. Then, the outputs from each of these modules are combined by using a Sugeno fuzzy integral. The experimental results obtained by using a database of 30 individual’s shows that the modular architecture can achieve a very high 98% recognition accuracy with a test set of 150 images. Therefore, we conclude that the proposed architecture provides a suitable platform to build a signature recognition system.


Modular neural networks Fuzzy integration Pattern recognition 


  1. 1.
    Ballard D (1981) Generalizing the hough transform to detect arbitrary shapes. Pattern Recognition Vol.13 No.2: 111–122zbMATHCrossRefGoogle Scholar
  2. 2.
    Zhang D (2000) Automated biometrics technologies and systems. Hong Kong Polytechnic University Ed. Kluwer Academic publishers Chapter 10: 203–206Google Scholar
  3. 3.
    Keller J, Gader P, Hocaoglu A (2000) Integrals in image processing and recognition. In: M. Grabisch, et al., eds., Fuzzy Measures and Integrals: Theory and Applications. Physica-Verlag, NY: 435–66Google Scholar
  4. 4.
    Grabisch M (1995) A new algorithm for identifying fuzzy measures and its application to pattern recognition. In Proc. of 4th IEEE Int. Conf. on Fuzzy Systems. Yokohama, Japan: 145–150Google Scholar
  5. 5.
    Grabisch M, Murofushi T, Sugeno M (2000) Fuzzy measures and integrals: Theory and Applications. Physica-Verlag, NY: 348–373zbMATHGoogle Scholar
  6. 6.
    Castillo O, Melin P, Kacprzyk J, Pedrycz W (2007) Hybrid intelligent systems analysis and design Ed. SpringerGoogle Scholar
  7. 7.
    Mendoza O, Melin P (2007) The fuzzy Sugeno integral as a decision operator in the recognition of images with modular neural networks. Tijuana Institute of Technology México Ed. SpringerGoogle Scholar
  8. 8.
    Melin P, Mancilla A, González C, Bravo D (2004) Modular neural networks with fuzzy Sugeno integral response integration for face and fingerprint recognition. The International MultiConference in Computer Science and Computer Engineering Las Vegas USA 1: 91–97Google Scholar
  9. 9.
    Melin P, Mancilla A, Lopez M, Solano D, Soto M, Castillo O (2007) Pattern recognition for industrial security using the fuzzy Sugeno integral and modular neural network. Soft Computing in Industrial Applications. Ed. Springer Berlin / Heidelberg 39: 4–9Google Scholar
  10. 10.
    Melin P, Felix C, Castillo O (2005) Face recognition using modular neural networks and the fuzzy Sugeno integral for response integration. Journal of Intelligent Systems 20(2): 275–229CrossRefGoogle Scholar
  11. 11.
    Melin P, Gonzalez C, Bravo D, Gonzalez F, Martinez G (2007) Modular neural networks and fuzzy Sugeno integral for pattern recognition. Then Case of Human Face and Fingerprint Tijuana Institute of Technology Tijuana Mexico Ed. SpringerGoogle Scholar
  12. 12.
    Melin P, Castillo O (2005) Hybrid intelligent systems for pattern recognition using soft computing. An Evolutionary Approach for Neural Networks and Fuzzy Systems (Studies in Fuzziness and Soft Computing) Ed. SpringerGoogle Scholar
  13. 13.
    Melin P, Castillo O (2005) Hybrid intelligent systems for pattern recognition. Ed. Springer-VerlagGoogle Scholar
  14. 14.
    Kung S, Mak M, Lin S (2005) Hiometric authentication a machine learning approach. Ed. Prentice Hall Information and System Sciences Series: 27–49Google Scholar
  15. 15.
    Santoso S, Powers E, Grady E (1997) Power quality disturbance data compression using wavelet transform methods IEEE Trans. On Power Delivery 12(3): 250–1257Google Scholar
  16. 16.
    Melin P, Kacprzyk J, Pedrycz W (2009) Bio-inspired hybrid intelligent systems for image analysis and pattern recognition. Springer-Verlag Heidelberg GermanyGoogle Scholar
  17. 17.
    Hernandez-Aguirre A, Monroy-Borja R, Reyes-garcia CA, Advances in Artficial Intelligence. Springer-Verlag LNAI 5845 GermanyGoogle Scholar

Copyright information

© Springer Berlin Heidelberg and Fuzzy Information and Engineering Branch of the Operations Research Society of China 2009

Authors and Affiliations

  • Mónica Beltrán
    • 1
  • Patricia Melin
    • 1
  • Leonardo Trujillo
    • 1
  1. 1.Graduate StudiesTijuana Institute of TechnologyTijuana BCMexico

Personalised recommendations