WRITER VERIFICATION BASED ON GRAPHOMETRIC FEATURES USING FEED-FORWARD NEURAL NETWORK

Carlos F. Romero, Carlos M. Travieso, Jesús B. Alonso, Miguel A. Ferrer

Abstract

This paper shows a writer verification automatic system based on a set of graphometric characteristics extracted from handwritten words. That dataset has been tested with our off-line handwritten database, which consists of 110 writers with 10 samples per writer, where a sample is a dataset of 34 words. After our experiments, we have got a verification success rate of 95.63% and Equal Error Rate (EER) of 3.90% is achieved. For previous results, we have used as classifiers a Neural Network, for each writer.

References

  1. Bishop, C.B., 1995. Neural Networks for Pattern Recognition, Oxford University Press.
  2. Juang, B.H., Rabiner, L.R., 1992. Spectral representations for speech recognition by neural networks-a tutorial. In Proceedings of the Workshop Neural Networks for Signal Processing, pp. 214 - 222.
  3. Romero, C.F., Travieso, C. M., Alonso, J. B., Ferrer, M. A., 2007. Using Off-line Handwritten Text for Writer Identification. In WSEAS Transactions on Signal Processing. Issue 1, Vol. 3, pp. 56-61.
  4. Cha, S. H., Srihari, S., 2000. Multiple feature integration for writer verification. In Proceedings Seventh Inernational. Workshop on Frontiers in Handwriting Recognition, pages 333-342.
  5. Leedham, G., Chachra, S., 2003. Writer Identification using Innovate Binarised Features of Handwritten Numerals. In Proceeding of the 7th International Conference on Document Analysis and Recognition. Vol. 1, pp. 413-416.
  6. Schlapbach, A., Bunke, H., 2004. Using HMM Based Recognizers for Writer Identification and Verification. In Proceeding of the 9th Int'l Workshop on Frontiers in Handwriting Recognition
  7. Bensefia, A., Paquet, T., Heutte, L., 2005. Handwritten Document Analysis for Automatic Writer Recognition. Electronic Letter on Computer Vision and Image Analysis, pp. 72-86.
  8. Bucalu, M., Shomaker, L., 2007. Text-Independent Writer Identification and Verification Using Textual and Allographic Features. In IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 29, No. 4.
  9. Otsu, N., 1979. A threshold selection method from graylevel histograms. In IEEE Transaction on Systems, Man and Cybernetics, Vol. 9, Is. 1, pp 62-66.
  10. Jaekyu Ha, R. M., Haralick, I. T., 1995. Document page decomposition by the bounding-box project, In Proceedings International Conference on Document Analysis and Recognition, Vol. 02, No. 2, p. 1119.
  11. Romero, C.F., Travieso, C. M., Alonso, J. B., Ferrer, M. A., 2009. Hybrid Parameterization System for Writer Identification. In Second International Conference on Bio-inspired Systems and Signal Processing, pp. 449- 454.
  12. Hertel, C., Bunke, H., 2003. A Set of Novel Features for Writer Identification. In Proceedings of the Audio and Video Based Biometric Person Authentication. pp. 679-687.
  13. 13. Srihari, S., Cha, S.H., Arora, H., Lee, S., 2001. Individuality of Handwriting: A Validity Study. In Proceedings of International Conference on Document Analysis and Recognition pp 106-109.
  14. 14. Morita, M.E. Facon, J. Bortolozzi, F. Garnes, S.J.A. Sabourin, R., 1999. Mathematical Morphology and Weighted Least Squares to Correcthandwriting Baseline Skew. In Proccedings of the 5th International Conference on Document Analysis and Recognition, pp. 430-433.
Download


Paper Citation


in Harvard Style

F. Romero C., Travieso C., Alonso J. and Ferrer M. (2010). WRITER VERIFICATION BASED ON GRAPHOMETRIC FEATURES USING FEED-FORWARD NEURAL NETWORK . In Proceedings of the Third International Conference on Bio-inspired Systems and Signal Processing - Volume 1: BIOSIGNALS, (BIOSTEC 2010) ISBN 978-989-674-018-4, pages 353-358. DOI: 10.5220/0002589003530358


in Bibtex Style

@conference{biosignals10,
author={Carlos F. Romero and Carlos M. Travieso and Jesús B. Alonso and Miguel A. Ferrer},
title={WRITER VERIFICATION BASED ON GRAPHOMETRIC FEATURES USING FEED-FORWARD NEURAL NETWORK },
booktitle={Proceedings of the Third International Conference on Bio-inspired Systems and Signal Processing - Volume 1: BIOSIGNALS, (BIOSTEC 2010)},
year={2010},
pages={353-358},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0002589003530358},
isbn={978-989-674-018-4},
}


in EndNote Style

TY - CONF
JO - Proceedings of the Third International Conference on Bio-inspired Systems and Signal Processing - Volume 1: BIOSIGNALS, (BIOSTEC 2010)
TI - WRITER VERIFICATION BASED ON GRAPHOMETRIC FEATURES USING FEED-FORWARD NEURAL NETWORK
SN - 978-989-674-018-4
AU - F. Romero C.
AU - Travieso C.
AU - Alonso J.
AU - Ferrer M.
PY - 2010
SP - 353
EP - 358
DO - 10.5220/0002589003530358