Advertisement

On-Line Signature Recognition Based on Reduced Set of Points

  • Iwona Kostorz
  • Rafal Doroz
Part of the Advances in Intelligent and Soft Computing book series (AINSC, volume 95)

Abstract

In the paper two methods of signature points reduction are presented. The reduction is based on selecting signature’s characteristic points. The first method is based on seeking points of the highest curvature using the IPAN99 algorithm. Parameters of the algorithm are selected automatically for each signature. The second method uses a comparative analysis of equal ranges of points in each signature. For both of methods the way of determination of characteristic points has been shown. As a result of experiments carried out the effectiveness of both methods and its usefulness for signature recognition and verification has been presented.

Keywords

Hide Markov Model Characteristic Point Signature Recognition Range Analysis Pattern Recognition Letter 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Al-Shoshan, A.I.: Handwritten Signature Verification Using Image Invariants and Dynamic Features. In: International Conference on Computer Graphics, Imaging and Visualisation. pp. 173–176 (2006)Google Scholar
  2. 2.
    Bajaj, R., Chaudhury, S.: Signature Verification Using Multiple Neural Classifiers. Pattern Recognition 30(1), 1–7 (1997)CrossRefGoogle Scholar
  3. 3.
    Bolle, R.M., Pankanti, S., Ratha, N.K., Connell, J.H.: Guide To Biometrics, p. 75. Springer, New York (2009)Google Scholar
  4. 4.
    Chetverikov, D., Szabo, Z.: Detection of high curvature points in plannar curves. In: 23rd Workshop of the Austrain Pattern Recognition Group, pp. 175–184 (1999)Google Scholar
  5. 5.
    Doroz, R., Porwik, P., Para, T., Wrobel, K.: Dynamic signature recognition based on velocity changes of some features. International Journal of Biometrics 1(1), 47–62 (2008)CrossRefGoogle Scholar
  6. 6.
    Doroz, R., Wrobel, K.: Method of Signature Recognition with the Use of the Mean Differences. In: Proceedings of the 31st International IEEE Conference on Information Technology Interfaces. Croatia, pp. 231–235 (2009)Google Scholar
  7. 7.
    Doroz, R., Kostorz, I.: The method for determining the characteristic points of Signatures based on IPAN99 algorithm. Journal of Medical Informatics and Technologies 15, 41–46 (2010)Google Scholar
  8. 8.
    El Yacoubi, A., Gilloux, M., Sabourin, R., Suen, C.: Unconstrained Hand Written Word Recognition using Hidden Markov Models. IEEE Transation on Pattern Analysis and Machine Intelligence 2(8), 752–760 (1999)CrossRefGoogle Scholar
  9. 9.
    Feng, H., Wah, C.H.: Online signature verification using a new extreme points warping technique Source. Pattern Recognition Letters 24, 2943–2951 (2003)CrossRefGoogle Scholar
  10. 10.
    Impedovo, S., Pirlo, G.: Verification of Handwritten Signatures: an Overview. In: 14th International Conference on Image Analysis and Processing, pp. 191–196 (2007)Google Scholar
  11. 11.
    Kato, N., Abe, M., Nemoto, Y.: A Handwritten Character Recognition System Using Modified Mahalanobis Distance. Trans. IEICE J79–D–II(1), 45–52 (1996)Google Scholar
  12. 12.
    Piyush Shankera, A., Rajagopalan, A.N.: Off-line signature verification using DTW. Pattern Recognition Letters 28, 1407–1414 (2007)CrossRefGoogle Scholar
  13. 13.
    Porwik, P.: The Compact Three Stages Method of the Signature Recognition. In: 6th International IEEE Conference on Computer Information Systems and Industrial Management Applications, pp. 282–287 (2007)Google Scholar
  14. 14.
    Schimke, S., Vielhauer, C., Dittmann, J.: Using Adapted Levenshtein Distance for On-Line Signature Authentication. In: Proceedings of the 17th International Conference, vol. 2, pp. 931–934 (2004)Google Scholar
  15. 15.
    Wirotius, M., Ramel, J., Vincent, N.: Selection of Points for On-Line Signature Comparison. In: International Workshop on Frontiers in Handwriting Recognition, Los Alamitos, CA, US, pp.1550–5235 (2004)Google Scholar
  16. 16.
    Wrobel, K., Doroz, R.: The new method of signature recognition based on least squares contour alignment. In: Proceedings of the International IEEE Conference on Biometrics and Kansei Engineering, pp. 80–83 (2009)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Iwona Kostorz
    • 1
  • Rafal Doroz
    • 1
  1. 1.Institute of Computer ScienceUniversity of SilesiaSosnowiecPoland

Personalised recommendations