Abstract
This work proposes a method of analysis of geometric features generated from hand-written text to verify a supposition that a given sample of text of unclear authorship (e.g., a signature or initials) and some given reference text of known authorship have been written by the same author. The method is targeted to problems where the reference material is relatively large and the sample of unclear authorship is small, hence the number of feature vectors for the two groups compared is highly unbalanced. This makes the problem computationally challenging as standard approaches based on statistical hypothesis testing to compare distributions cannot be used. We propose a method to estimate the likelihood that the set of features observed in the small sample comes from the distribution generated from the reference material. This approach can be used to help discover or prove a forgery in documents.
Access provided by Autonomous University of Puebla. Download to read the full chapter text
Chapter PDF
Similar content being viewed by others
References
Bahlmann, C., Haasdonk, B., Burkhardt, H.: Online handwriting recognition with support vector machines - a kernel approach. In: Proc of the Eighth International Workshop on Frontiers in Handwriting Recognition, pp. 49–54 (2002), doi:10.1109/IWFHR.2002.1030883
Hastie, T., Tibshirani, R., Friedman, J.: The Elements of Statistical Learning – Data Mining, Inference, and Prediction. Springer, Heidelberg (2001)
Katalog Graficznych Cech Pisma Ręcznego (The Catalogue of Graphic Features of Handwriting) (in Polish) (2007), http://prawo.amu.edu.pl/uploads/slownik/aneks.htm (accessed March 12, 2011)
Koziczak, A.: Metody pomiarowe w badaniach pismoznawczych (Measurement methods in examination of handwriting, in Polish), Instytut Ekspertyz Sądowych, Kraków (1997)
Morris, R.: Forensic handwriting identification. Fundamental concepts and principles. Academic Press, New York (2000)
Saferstein, R.: Criminalistic: An Introduction to Forensic Science, 8th edn. Prentice-Hall, Englewood Cliffs (2004)
Schlapbach, A., Bunke, H.: A writer identification and verification system using HMM based recognizers. Pattern Analysis & Applications 10(1), 33–43 (2007), doi:10.1007/s10044-006-0047-5
Xu, L., Krzyzak, A., Suen, C.Y.: Methods of combining multiple classifiers and their applications to handwriting recognition. IEEE Trans on Systems, Man and Cybernetics 22(3), 418–435 (2002)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Maciejewski, H., Ptak, R. (2011). Analysis of Geometric Features of Handwriting to Discover a Forgery. In: Zamojski, W., Kacprzyk, J., Mazurkiewicz, J., Sugier, J., Walkowiak, T. (eds) Dependable Computer Systems. Advances in Intelligent and Soft Computing, vol 97. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-21393-9_11
Download citation
DOI: https://doi.org/10.1007/978-3-642-21393-9_11
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-21392-2
Online ISBN: 978-3-642-21393-9
eBook Packages: EngineeringEngineering (R0)