Advertisement

Type-2 Fuzzy Logic for Improving Training Data and Response Integration in Modular Neural Networks for Image Recognition

  • Olivia Mendoza
  • Patricia Melin
  • Oscar Castillo
  • Guillermo Licea
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4529)

Abstract

The combination of Soft Computing techniques allows the improvement of intelligent systems with different hybrid approaches. In this work we consider two parts of a Modular Neural Network for image recognition, where a Type-2 Fuzzy Inference System (FIS 2) makes a great difference. The first FIS 2 is used for feature extraction in training data, and the second one to find the ideal parameters for the integration method of the modular neural network. Once again Fuzzy Logic is shown to be a tool that can help improve the results of a neural system, when facilitating the representation of the human perception.

Keywords

Membership Function Fuzzy Inference System Image Recognition Soft Computing Technique Modular Neural Network 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Salinas, R., Larraguibel, L.: Red Neuronal de Arquitectura Paramétrica en Reconocimiento de Rostros. Divulgacion Electronica de las Ciencias, vol.17 (2002), http://cabierta.uchile.cl/revista/17/articulos/articulos.html
  2. 2.
    Melin, P., Castillo, O.: Hybrid Intelligent Systems for Pattern Recognition. Springer, Heidelberg (2005)zbMATHGoogle Scholar
  3. 3.
    Yang, P., Du, B., Shan, S., Gao, W.: A Novel Pupil Localization Method Based On Gaboreye Model And Radial Symmetry Operator. ICT-ISVISION Joint R&D Laboratory for Face Recognition, Beijing, China (2004)Google Scholar
  4. 4.
    Starovoitov, V.V., Samal, D.I., Briliuk, D.V.: Three Approaches for Face Recognition. In: The 6-th International Conference on Pattern Recognition and Image Analysis, Velikiy Novgorod, Russia, pp. 707–711 (2002)Google Scholar
  5. 5.
    Dowdalla, J.B., Pavlidisa, I., Bebisb, G.: Face Detection in the Near-IR Spectrum, Dept. of Computer Science, University of Nevada, Reno, NV (2003)Google Scholar
  6. 6.
    Chuang, M.-M., Chang, R.-F., Huang, Y.-L.: Automatic Facial Feature Extraction in Model-based Coding. Journal of Information Science and Engineering 16, 447–458 (2000)Google Scholar
  7. 7.
    Mendoza, O., Melín, P.: Sistema para el Modelado Diseño y Pruebas de Arquitecturas Neuronales Multi-Red. In: International Seminar on Computational Intelligence, Tijuana, México, pp. 88–98 (2004)Google Scholar
  8. 8.
    Melin, P., Mancilla, A., Lopez, M., Mendoza, O.: A hybrid modular neural network architecture with fuzzy Sugeno integration for time series forecasting. Journal of Applied Soft Computing, in Press, Corrected Proof (2007)Google Scholar
  9. 9.
    Mendoza, O., Melin, P.: The Fuzzy Sugeno Integral as a Decision Operator in the Recognition of Images with Modular Neural Networks. In: Hybrid Intelligent Systems: Design and Analysis, pp. 299–310. Springer, Heidelberg (2007)Google Scholar
  10. 10.
    AT&T Laboratories Cambridge: The ORL database of faces, http://www.cl.cam.ac.uk/research/dtg/attarchive/facedatabase.html
  11. 11.
    Mendoza, O., Melín, P.: Sistemas de Inferencia Difusos Tipo-1 y Tipo-2 Aplicados a la Detección de Bordes en Imágenes Digitales. In: International Seminar on Computational Intelligence 2006 IEEE-CIS chapter Mexico, Tijuana, Mexico, pp. 117–123 (2006)Google Scholar
  12. 12.
    Mendel, J.: Uncertain Rule-Based Fuzzy Logic Systems: Introduction and New Directions. Prentice-Hall, Englewood Cliffs (2001)zbMATHGoogle Scholar
  13. 13.
    Castillo, O., Melin, P., Kacprzyk, J., Pedrycz, W.: Hybrid Intelligent Systems: Design and Analysis. Springer, Heidelberg (2007)zbMATHGoogle Scholar
  14. 14.
    Miosso, C.J., Bauchspiess, A.: Fuzzy Inference System Applied to Edges Detection in Digital Images. In: V Brazilian Conference on Neural Networks, Brasil (2001)Google Scholar
  15. 15.
    Castro-Rodríguez, J.R., Castillo-López, O., Martínez-Méndez, L.G.: Tool Box para Lógica Difusa Tipo-2 por Intervalos. In: International Seminar on Computational Intelligence 2006 IEEE - CIS Mexico Chapter, Tijuana, Mexico, pp. 100–108 (2006)Google Scholar
  16. 16.
    Sharkey, A.J.C.: Ensemble and Modular Multi-Net Systems. In: Sharkey, A.J.C. (ed.) Combining Artificial Neural Nets, pp. 1–25. Springer, Heidelberg (1999)Google Scholar
  17. 17.
    The Math Works, Inc.: Neural Network Toolbox (1994-2006), available on the web page: http://www.mathworks.com/products/neuralnet/Google Scholar
  18. 18.
    Detyniecki, M.: Mathematical Aggregation Operators and Their Application to Video Querying. PHD Artificial Intelligence, Pierre and Marie Curie University, Paris (2000)Google Scholar

Copyright information

© Springer Berlin Heidelberg 2007

Authors and Affiliations

  • Olivia Mendoza
    • 1
  • Patricia Melin
    • 2
  • Oscar Castillo
    • 2
  • Guillermo Licea
    • 1
  1. 1.Universidad Autonoma de Baja California, TijuanaMexico
  2. 2.Tijuana Institute of Technology, TijuanaMexico

Personalised recommendations