Your browser does not support JavaScript!
http://iet.metastore.ingenta.com
1887

access icon free A robust dissimilarity representation for writer-independent signature modelling

© The Institution of Engineering and Technology
Received 25/01/2013, Accepted 28/05/2013, Revised 11/04/2013, Published

In this study, the authors present a novel dissimilarity-based signature modelling framework for writer-independent off-line signature verification. The proposed framework utilises a discrete Radon transform and a dynamic time warping algorithm for writer-independent signature representation in dissimilarity space, and a writer-specific strategy for dissimilarity normalisation. A discriminative classifier, either a discriminant function or a support vector machine, is utilised for verification purposes. Both linear and non-linear decision boundaries are considered. The authors show that the novel techniques presented in this study provide an improved platform for writer-independent signature modelling. When evaluated on Dolfing's data set, a signature database that contains 1530 genuine signatures and 3000 amateur skilled forgeries, the systems presented in this study outperform all previous systems also evaluated on this data set.

Inspec keywords: Radon transforms; support vector machines; digital signatures; image representation; image classification; discrete transforms; handwriting recognition

Other keywords: dynamic time warping algorithm; discriminative classifier; dissimilarity-based signature modelling; dissimilarity representation; support vector machine; writer-independent signature representation; Dolfing data set; discrete Radon transform; dissimilarity normalisation; signature database; nonlinear decision boundary; dissimilarity space; writer-independent offline signature verification; writer specific strategy; discriminant function; linear decision boundary

Subjects: Integral transforms; Image recognition; Computer vision and image processing techniques; Integral transforms; Data security; Cryptography

References

    1. 1)
      • 16. Jayadevan, R., Kohe, S., Patil, P.: ‘Dynamic time warping based static hand printed signature verification’, Pattern Recognit. Res., 2009, 4, (1), pp. 52–65 (doi: 10.13176/11.127).
    2. 2)
      • 21. Bouveyron, C., Girard, S., Schmid, C.: ‘High-dimensional discriminant analysis’, Commun. Stat. Theory Methods, 2007, 36, (14), pp. 2607–2623 (doi: 10.1080/03610920701271095).
    3. 3)
      • 5. Impedovo, D., Pirlo, G.: ‘Automatic signature verification: the state of the art’, IEEE Trans. Syst. Man Cybern. C, Appl. Rev., 2008, 38, (5), pp. 609–635 (doi: 10.1109/TSMCC.2008.923866).
    4. 4)
      • 8. Justino, E., Bortolozzi, F., Sabourin, R.: ‘A comparison of svm and hmm classifiers in the off-line signature verification’, Pattern Recognit. Lett., 2005, 26, (9), pp. 1377–1385 (doi: 10.1016/j.patrec.2004.11.015).
    5. 5)
      • 1. Toft, P.: ‘The radon transform: theory and implementation’. PhD thesis, Technical University of Denmark, 1996.
    6. 6)
      • 7. Santos, C., Justino, E., Bortolozzi, F., Sabourin, R.: ‘An off-line signature verification system based on the questioned document expert's approach and a neural network classifier’. Int. Workshop on Frontiers in Handwriting Recognition, 2004, pp. 498–502.
    7. 7)
      • 22. Swanepoel, J., Coetzer, J.: ‘Off-line signature verification using flexible grid features and classifier fusion’. Int. Conf. Frontiers in Handwriting Recognition, 2010, pp. 297–302.
    8. 8)
      • 17. Coetzer, J., Herbst, B., du Preez, J.: ‘Offine signature verification using the discrete radon transform and a hidden markov model’, Eur. Assoc. Signal Process. J. Appl. Signal Process., 2004, 4, pp. 559–571 (doi: 10.1155/S1110865704309042).
    9. 9)
      • 11. Eskander, G., Sabourin, R., Granger, E.: ‘Adaptation of writer-independent systems for offline signature verification’. Int. Conf. Frontiers in Handwriting Recognition, 2012.
    10. 10)
      • 9. Batista, L., Granger, E., Sabourin, R.: ‘Applying dissimilarity representation to off-line signature verification’. Int. Conf. Pattern Recognition, 2010, pp. 1293–1297.
    11. 11)
      • 2. Rabiner, L., Schmidt, C.: ‘Application of dynamic time warping to connected digit recognition’, IEEE Trans. Acoust. Speech Signal Process., 1980, 28, (4), pp. 377–388 (doi: 10.1109/TASSP.1980.1163422).
    12. 12)
      • 25. Zhang, S., Hossain, M., Hassan, M., Bailey, J., Ramamohanarao, K.: ‘Feature weighted svms using receiver operating characteristics’. Society for Industrial and Applied Mathematics Int. Conf. Data Mining, 2009, pp. 497–508.
    13. 13)
      • 26. Liang, J., Yang, S., Winstanley, A.: ‘Invariant optimal feature selection: a distance discriminant and feature ranking based solution’, Pattern Recognit., 2008, 41, (5), pp. 1429–1439 (doi: 10.1016/j.patcog.2007.10.018).
    14. 14)
      • 23. Panton, M., Coetzer, J.: ‘Off-line signature verification using ensembles of local radon transform-based hmms’. Annual Symp. Pattern Recognition Association of South Africa, 2010, pp. 201–206.
    15. 15)
      • 20. Coetzer, J.: ‘Off-line signature verification’. PhD thesis, Stellenbosch University, 2005.
    16. 16)
      • 27. Nguyen, M., De la Torre, F.: ‘Optimal feature selection for support vector machines’, Pattern Recognit., 2010, 43, (3), pp. 584–591 (doi: 10.1016/j.patcog.2009.09.003).
    17. 17)
      • 19. Platt, J.: ‘Sequential minimal optimization: a fast algorithm for training support vector machines’, Microsoft Res., 1998.
    18. 18)
      • 18. Jain, A., Nandakumar, K., Ross, A.: ‘Score normalization in multimodal biometric systems’, Pattern Recognit., 2005, 38, pp. 2270–2285 (doi: 10.1016/j.patcog.2005.01.012).
    19. 19)
      • 12. Swanepoel, J., Coetzer, J.: ‘Writer-specific dissimilarity normalisation for improved writer-independent off-line signature verification’. Int. Conf. Frontiers in Hand-writing Recognition, 2012, pp. 391–396.
    20. 20)
      • 3. Friedman, J.: ‘Regularized discriminant analysis’, J. Am. Stat. Assoc., 1989, 84, (405), pp. 165–175 (doi: 10.1080/01621459.1989.10478752).
    21. 21)
      • 24. Chang, Y., Lin, C.: ‘Feature ranking using linear svm’, Causation Predict. Chall. Chall. Mach. Learn., 2008, 2, pp. 47–57.
    22. 22)
      • 10. Kumar, R., Sharma, J., Chanda, B.: ‘Writer-independent off-line signature verification using surroundedness feature’, Pattern Recognit. Lett., 2011, 33, (3), pp. 301–308 (doi: 10.1016/j.patrec.2011.10.009).
    23. 23)
      • 6. Impedovo, D., Pirlo, G., Plamondon, R.: ‘Handwritten signature verification: new advancements and open issues’. Int. Conf. Frontiers in Handwriting Recognition, 2012, pp. 365–370.
    24. 24)
      • 13. Dolfing, J., Aarts, E., van Oosterhout, J.: ‘On-line signature verification with hidden markov models’. Int. Conf. Pattern Recognition, 1998, vol. 2, pp. 1309–1312.
    25. 25)
      • 4. Vapnik, V.: ‘The nature of statistical learning theory’ (Springer-Verlag, 1995).
    26. 26)
      • 15. Piyush Shanker, A., Rajagopalan, A.: ‘Off-line signature verification using dtw’, Pattern Recognit. Lett., 2007, 28, (12), pp. 1407–1414 (doi: 10.1016/j.patrec.2007.02.016).
    27. 27)
      • 14. Fang, B., Leung, C., Tang, Y., Tse, K., Kwok, P., Wong, Y.: ‘Off-line signature verification by the tracking of feature and stroke positions’, Pattern Recognit., 2003, 36, (1), pp. 91–101 (doi: 10.1016/S0031-3203(02)00061-4).
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-bmt.2013.0011
Loading

Related content

content/journals/10.1049/iet-bmt.2013.0011
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading
Print this page
This is a required field
Please enter a valid email address