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

Published in Journal Articles

Abstract

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.

  1. Mónica Beltrán, Patricia Melin and Leonardo Trujillo. Development of modular neural networks with fuzzy logic response integration for signature recognition. Fuzzy Information and Engineering 1(4):345-355, 2009. URL, DOI BibTeX

    @article{,
    	year = 2009,
    	issn = "1616-8658",
    	journal = "Fuzzy Information and Engineering",
    	volume = 1,
    	number = 4,
    	doi = "10.1007/s12543-009-0027-8",
    	title = "Development of modular neural networks with fuzzy logic response integration for signature recognition",
    	url = "http://dx.doi.org/10.1007/s12543-009-0027-8",
    	publisher = "Springer-Verlag",
    	keywords = "Modular neural networks; Fuzzy integration; Pattern recognition",
    	author = "Beltrán, Mónica and Melin, Patricia and Trujillo, Leonardo",
    	pages = "345-355",
    	language = "English"
    }
    

Read more...
Subscribe to this RSS feed
Feedback