Advertisement

Signature Verification by View-Based Feature Extractor and DTW Classifier

  • Khalid Saeed
  • Marcin Adamski
Conference paper

Abstract

This paper presents a human identifying system on the basis of their signature image analysis. For feature extraction, the system uses the view-based approach with one of the three versions of Dynamic Time Warping (DTW) method. The experiments are carried out for each of the three versions of DTW and use various combinations of feature vectors. The average percentage of properly classified signatures has achieved 84%

Keywords

Feature Vector Dynamic Time Warping Speak Word Recognition Signature Verification Cumulative Distance 
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]
    Ferrer M. A., Alonso J. B., Travieso C. M.: Offline Geometric Parameters for Automatic Signature Verification Using Fixed-Point Arithmetic. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 27, no. 6, 2005, pp. 993-997.CrossRefGoogle Scholar
  2. [2]
    Lee L., Berger T., Aviczer E.: Reliable on-line Human Signature Verification Systems. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 18, no. 6, 1996, pp. 643-647.CrossRefGoogle Scholar
  3. [3]
    Saeed K.: Efficient Method for On-Line Signature Verification. Proceedings of the International Conference on Computer Vision and Graphics - ICCVG’02, vol. 2, Zakopane, Poland, 2002, pp. 25-29.Google Scholar
  4. [4]
    Munich M.E., Perona P.: Visual identification by signature tracking. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 25, no. 2, 2003, pp. 200-217.CrossRefGoogle Scholar
  5. [5]
    Saeed K.: Image Analysis for Object Recognition. Bialystok Technical University Press, Bialystok, Poland, 2004.Google Scholar
  6. [6]
    Saeed K., Predko A., Rybnik M.: A Projection-Based Criterion for Polish Script Identification. Computing, Multimedia and Intelligent Techniques, vol. 1, no. 1, 2006.Google Scholar
  7. [7]
    Saeed K., Adamski M.: Offline signature classification with DTW application. XIV Conference on Informatics Systems - KBIB’05 (in Polish), vol. 1, pp. 455-460.Google Scholar
  8. [8]
    Tabedzki M., Saeed K.: View-Based Word Recognition System. International Conference on Neural Networks and Artificial Intelligence, Brest, Belarus, 2006, pp. 145-148.Google Scholar
  9. [9]
    Adamski M., Saeed K.: Classification of handwritten signatures based on boundary tracing. International Conference on Neural Networks and Artificial Intelligence, Brest, Belarus, 2006, pp. 201-205.Google Scholar
  10. [10]
    Sakoe H., Chiba S.: Dynamic Programming Algorithm Optimization for Spoken Word Recognition. IEEE Transactions on Acoustics, Speech, and Signal Processing, vol. 26, no. 1, 1978, pp. 43-49.MATHCrossRefGoogle Scholar
  11. [11]
    Keogh E. J., Pazzani M. J.: Derivative Dynamic Time Warping. First SIAM International Conference on Data Mining Proceedings, Chicago, IL, USA, 2001, pp. 187-194.Google Scholar
  12. [12]
    Santos C., Justino E. J. R., Bortolozzi F., Sabourin R.: An Off-Line Signature Verification Method Based on the Questioned Document Expert’s Approach and a Neural Network Classifier. Proceedings of the Ninth International Workshop on Frontiers in Handwriting Recognition, IEEE, USA, Washington DC, 2004, pp. 498-502.Google Scholar

Copyright information

© Springer Science+Business Media, LLC 2007

Authors and Affiliations

  • Khalid Saeed
    • 1
  • Marcin Adamski
    • 1
  1. 1.Faculty of Computer Science, Bialystok Technical UniversityWiejska 45APoland

Personalised recommendations