Off-line signature verification without requiring random forgeries for training

  • Nabeel A. MurshedEmail author
  • Flávio Bortolozzi
  • Robert Sabourin
Session IA1b — Feature Matching & Detection
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1024)


This paper presents an Off-line Signature Verification System for the elimination of random forgeries. Compared with the proposed systems thus far, our system is trained with genuine signatures only. This eliminates many of the problems existent in the current systems. The proposed system is evaluated with a data base of 200 signatures.


False Acceptance Rate False Rejection Rate Fuzzy ARTMAP Genuine Signature Handwritten Signature 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    D. A. Mighell, T. S. Wilkinson and J. W. Goodman. Backpropagation and its application to handwritten signature verification. Tourtzkey, D. (Ed), Advances in Neural Information Processing Systems 1, pp. 341–347, Morgan Kaufman, 1989.Google Scholar
  2. 2.
    D. K. R. McCormack and B. M. Brown. Handwritten signature verification using the Backpropagation neural network. In Neural Computing Research and Applications: Part Two, pp. 243–251, Queen's University of Belfast, N. Ireland, 1992.Google Scholar
  3. 3.
    G. A. Carpenter, S. Grossberg, N. Markuzon, and J. H. Reynolds. Fuzzy ARTMAP: A neural network architecture for incremental supervised learning of analog multidimensional maps. IEEE Tran. Neural Networks. Vol. 3. No. 5. 698–713, 1992.Google Scholar
  4. 4.
    G. W. Cottrell, P. Munro, and D. Zipser. Image Compression by back propagation: an example of exlensional programming. Advances in Cognitive Sciences, 3, Sharkey, N.E. (Ed), Norwood, NJ, 1989.Google Scholar
  5. 5.
    H. Cardot, M. Revenu, B. Victorri, and M. Revillet. An artificial neural network a rehi tecture for handwritten signature authentication, SEPT, 42 rue des Coutures, 14000 Caen, France, 1992.Google Scholar
  6. 6.
    N. Ostu. A threshold selection method from gray-level histograms. IEEE Trans. Syst. Man. Cybernetics, Vol. SMC-9, NO. 1, 62–66, 1979.Google Scholar
  7. 7.
    R. Plamondon and G. Lorette. Automatic Signature Verification and Writer Identification: The State of The Art. Pattern Recognition, Vol. 22. No. 2, 107–131, 1989.Google Scholar
  8. 8.
    R. Sabourin, M. Cheriet and G. Genest. An Extended-Shadow-Code Based Approach For Oil-Line Signature Verification. Proc. 2nd. Int. Conf. Doc. Ananlysis and Recognition., pp. 1–6, Tsukuba science city, Japan, October 20–22, 1993.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1995

Authors and Affiliations

  • Nabeel A. Murshed
    • 1
    Email author
  • Flávio Bortolozzi
    • 1
  • Robert Sabourin
    • 2
  1. 1.Centro Federal de EducaÇÃo Tecnológica do Parana (CEFET-PR)Pontifícia Universidadc Católica do Parana (PUC-PR)Curitiba - ParanáBrasil
  2. 2.école de Technologie SupérieureMontréalCanada

Personalised recommendations