Signature Recognition with a Hybrid Approach Combining Modular Neural Networks and Fuzzy Logic for Response Integration

Book Chapters

  1. Mónica Beltrán, Patricia Melin and Leonardo Trujillo. Signature Recognition with a Hybrid Approach Combining Modular Neural Networks and Fuzzy Logic for Response Integration. In Oscar Castillo, Witold Pedrycz and Janusz Kacprzyk (eds.). Evolutionary Design of Intelligent Systems in Modeling, Simulation and Control. Studies in Computational Intelligence series, volume 257, Springer Berlin Heidelberg, 2009, pages 185-201. URL, DOI BibTeX

    @incollection{,
    	year = 2009,
    	isbn = "978-3-642-04513-4",
    	booktitle = "Evolutionary Design of Intelligent Systems in Modeling, Simulation and Control",
    	volume = 257,
    	series = "Studies in Computational Intelligence",
    	editor = "Castillo, Oscar and Pedrycz, Witold and Kacprzyk, Janusz",
    	doi = "10.1007/978-3-642-04514-1_10",
    	title = "Signature Recognition with a Hybrid Approach Combining Modular Neural Networks and Fuzzy Logic for Response Integration",
    	url = "http://dx.doi.org/10.1007/978-3-642-04514-1_10",
    	publisher = "Springer Berlin Heidelberg",
    	author = "Beltrán, Mónica and Melin, Patricia and Trujillo, Leonardo",
    	pages = "185-201"
    }
    

Abstract

This chapter describes a modular neural network (MNN) with fuzzy integration for the problem of signature recognition. Currently, biometric identification has gained a great deal of research interest within the pattern recognition community [59]. 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 a 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 using a Sugeno fuzzy integral and a fuzzy inference system [65]. The experimental results obtained using a database of 30 individual’s shows that the modular architecture can achieve a very high 99.33% 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. Furthermore we consider the verification of signatures as false acceptance, false rejection and error recognition of the MNN.

Published in
Evolutionary Design of Intelligent Systems in Modeling, Simulation and Control
Studies in Computational Intelligence
Pages 185-201
Chapter 10
Volume 257
http://link.springer.com/chapter/10.1007/978-3-642-04514-1_10
Copyright
2009
ISSN
1860-949X
ISBN
978-3-642-04514-1
Last modified onSaturday, 12 October 2013 17:26
(0 votes)
Read 3151 times
Log in
G+