Abstract
The individuality of handwriting is the principal underpinning of forensic handwriting examination. Studies of individuality have considered different statistical extremes to obtain handwriting samples. The first is a representative population drawn from a country. The second is a population of twins– so as to reflect genetic similarity. A third approach is to study whether teachers and schools have an influence on individuality. This paper presents preliminary results of individuality studies with data from children’s handwriting, in grades 2–4, to identify the school, teacher and student. Considering the single handwritten word and we evaluate the performances of two methods, one based on feature values assigned by human questioned document examiners and the other based on automatically computing image features. Results are given for determining the school, the teacher and the student from images using restricted Boltzmann machines. Results of identifying the school with human assigned features and support vector machines are also given.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Hilton, O.: Scientific Examination of Questioned Documents, Revised Edition. CRC Press, New York (1993)
Hinton, G.E., Salakhutdinov, R.R.: Reducing the dimensionality of data with neural networks. Science 313(5786), 504–507 (2006)
Hinton, G.E.: Training products of experts by minimizing contrastive divergence. Neural Comput. 14(8), 1771–1800 (2002)
Huber, R.A., Headrick, A.M.: Handwriting Identification: Facts and Fundamentals. CRC Press, Boca Raton (1999)
Kelly, J.S., Lindblom, B.: Scientific Examination of Questioned Documents, 2nd edn. CRC Press, Boca Raton (2006)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems (2012)
Larochelle, H., Bengio, Y.: Classification using discriminative restricted Boltzmann machines. In: Proceedings of the 25th International Conference on Machine Learning, ICML 2008, pp. 536–543. ACM, New York (2008)
LeCun, Y., Boser, B., Denker, J.S., Henderson, D., Howard, R.E., Hubbard, W., Jackel, L.D.: Backpropagation applied to handwritten Zip Code recognition. Neural Comput. 1(4), 541–551 (1989)
Puri, M., Srihari, S.N., Hanson, L.: Probabilistic modeling of children’s handwriting. In: Document Recognition and Retrieval XX. SPIE (2014)
Osborn, A.: Questioned Documents. Nelson Hall Pub, Chicago (1929)
Rashid, S.F., Schambach, M.P., Rottland, J., von der Nüll, S.: Low resolution arabic recognition with multidimensional recurrent neural networks. In: Proceedings of the 4th International Workshop on Multilingual OCR, MOCR 2013, pp. 6:1–6:5. ACM, New York (2013)
Salakhutdinov, R., Mnih, A., Hinton, G.: Restricted Boltzmann machines for collaborative filtering. In: Proceedings of the 24th International Conference on Machine Learning, ICML 2007, pp. 791–798. ACM, New York (2007)
Srihari, S.N., Cha, S., Arora, H., Lee, S.: Individuality of handwriting. J. Forensic Sci. 44(4), 856–872 (2002)
Srihari, S.N., Huang, C., Srinivasan, H.: On the discriminability of the handwriting of twins. J. Forensic Sci. 53(2), 430–446 (2008)
Xu, Z., Srihari, S.: Bayesian network structure learning using causality. In: Submitted (2014)
Acknowledgement
The work was supported by Award No. 2010-DN-BX-K212 of the NIJ, Office of Justice Programs, U.S. DoJ. The opinions expressed are those of the author(s) and do not necessarily reflect those of the DoJ.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Srihari, S.N., Chen, G., Xu, Z., Hanson, L. (2015). Studies in Individuality: Can Students, Teachers and Schools Be Determined from Children’s Handwriting?. In: Garain, U., Shafait, F. (eds) Computational Forensics. IWCF IWCF 2012 2014. Lecture Notes in Computer Science(), vol 8915. Springer, Cham. https://doi.org/10.1007/978-3-319-20125-2_3
Download citation
DOI: https://doi.org/10.1007/978-3-319-20125-2_3
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-20124-5
Online ISBN: 978-3-319-20125-2
eBook Packages: Computer ScienceComputer Science (R0)