How to Define Local Shape Descriptors for Writer Identification and Verification

Imran Siddiqi, Nicole Vincent

Abstract

This paper presents an effective method for writer identification and verification in handwritten documents. The idea is that within a handwritten text, there exist certain redundant patterns that a particular writer would use frequently as he writes and these forms could be exploited to recognize the au- thorship of a document. To extract these patterns, the text is divided into a large number of small sub-images and a set of shape descriptors is extracted from each. Similar patterns are then clustered together for which a number of clustering techniques have been evaluated. The writer of the unknown document is identified by Bayesian classifier. The system trained and tested on 55 docu- ments of the same number of authors, exhibited promising results.

References

  1. A. Bensefia, T. Paquet and L. Heutte: A writer identification and verification system, Pattern Recognition Letters, Elsevier Science Inc. New York, Vol 26, issue 13, (2005) 2080- 2092
  2. V. Bouletreau, N. Vincent, R. Sabourin, H. Emptoz: Handwriting and signature: one or two personality identifiers?, In Proc.of Fourteenth International Conference on Pattern Recognition, Los Alamitos, CA, vol.2, (1998) 1758-1760
  3. M. Bulacu, L. Schomaker, and L. Vuurpijl: Writer identification using edge-based directional features, In Proc. of 7th International Conference on Document Analysis and Recognition, volume II, Edinburgh, Scotland, (2003) 937-941
  4. U. Marti and H. Bunke, “A full English sentence database for off-line handwriting recognition”, In Proc. of 5th International Conference on Document Analysis and Recognition, Bangalore, India, (1999) 705-708
  5. A. Nosary, L. Heutte, T. Paquet, Y. Lecourtier, "Defining writer's invariants to adapt the recognition task", In Proc. of 5th International Conference on Document Analysis and Recognition, Bangalore, India, (1999) 765-768
  6. N. Päivinen: Clustering with a minimum spanning tree of scale-free-like structure, Pattern Recognition Letters, Vol. 26 , Issue 7, Elsevier Science Inc. New York, (2005) 921-930
  7. R. Plamondon and G. Lorette, “Automatic signature verification and writer identification - the state of the art”, Pattern Recognition, vol. 22, n°2, (1989) 107-131
  8. H.E.S. Said, T.N Tan, K.D. Baker, “Personal Identification Based on Handwriting”, Pattern Recognition, vol. 33, (2000) 149-160.
  9. A. Seropian and N. Vincent, "Writers Authentication and Fractal Compression", Eighth International Workshop on Frontiers in Handwriting Recognition (IWFHR'02), (2002)
  10. I. Siddiqi and N. Vincent: Writer Identification in Handwritten Documents, In Proc. of the 9th Int'l conference on Document Analysis and Recognition (ICDAR 07), Curitiba, Brazil, (2007) 108-112
  11. S. Srihari, S. Cha, H. Arora, and S. Lee, “Individuality of handwriting”, J. of Forensic Sciences, 47(4):1.17, (2002)
Download


Paper Citation


in Harvard Style

Siddiqi I. and Vincent N. (2008). How to Define Local Shape Descriptors for Writer Identification and Verification . In Proceedings of the 8th International Workshop on Pattern Recognition in Information Systems - Volume 1: PRIS, (ICEIS 2008) ISBN 978-989-8111-42-5, pages 199-204. DOI: 10.5220/0001729301990204


in Bibtex Style

@conference{pris08,
author={Imran Siddiqi and Nicole Vincent},
title={How to Define Local Shape Descriptors for Writer Identification and Verification},
booktitle={Proceedings of the 8th International Workshop on Pattern Recognition in Information Systems - Volume 1: PRIS, (ICEIS 2008)},
year={2008},
pages={199-204},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001729301990204},
isbn={978-989-8111-42-5},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 8th International Workshop on Pattern Recognition in Information Systems - Volume 1: PRIS, (ICEIS 2008)
TI - How to Define Local Shape Descriptors for Writer Identification and Verification
SN - 978-989-8111-42-5
AU - Siddiqi I.
AU - Vincent N.
PY - 2008
SP - 199
EP - 204
DO - 10.5220/0001729301990204