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.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
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
Melin, P., Castillo, O.: Hybrid Intelligent Systems for Pattern Recognition. Springer, Heidelberg (2005)
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)
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)
Dowdalla, J.B., Pavlidisa, I., Bebisb, G.: Face Detection in the Near-IR Spectrum, Dept. of Computer Science, University of Nevada, Reno, NV (2003)
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)
Mendoza, O., MelÃn, 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)
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)
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)
AT&T Laboratories Cambridge: The ORL database of faces, http://www.cl.cam.ac.uk/research/dtg/attarchive/facedatabase.html
Mendoza, O., MelÃn, 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)
Mendel, J.: Uncertain Rule-Based Fuzzy Logic Systems: Introduction and New Directions. Prentice-Hall, Englewood Cliffs (2001)
Castillo, O., Melin, P., Kacprzyk, J., Pedrycz, W.: Hybrid Intelligent Systems: Design and Analysis. Springer, Heidelberg (2007)
Miosso, C.J., Bauchspiess, A.: Fuzzy Inference System Applied to Edges Detection in Digital Images. In: V Brazilian Conference on Neural Networks, Brasil (2001)
Castro-RodrÃguez, J.R., Castillo-López, O., MartÃnez-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)
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)
The Math Works, Inc.: Neural Network Toolbox (1994-2006), available on the web page: http://www.mathworks.com/products/neuralnet/
Detyniecki, M.: Mathematical Aggregation Operators and Their Application to Video Querying. PHD Artificial Intelligence, Pierre and Marie Curie University, Paris (2000)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer Berlin Heidelberg
About this paper
Cite this paper
Mendoza, O., Melin, P., Castillo, O., Licea, G. (2007). Type-2 Fuzzy Logic for Improving Training Data and Response Integration in Modular Neural Networks for Image Recognition. In: Melin, P., Castillo, O., Aguilar, L.T., Kacprzyk, J., Pedrycz, W. (eds) Foundations of Fuzzy Logic and Soft Computing. IFSA 2007. Lecture Notes in Computer Science(), vol 4529. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-72950-1_60
Download citation
DOI: https://doi.org/10.1007/978-3-540-72950-1_60
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-72917-4
Online ISBN: 978-3-540-72950-1
eBook Packages: Computer ScienceComputer Science (R0)