Offline Signature Verification by Combining Graph Edit Distance and Triplet Networks

  • Paul MaergnerEmail author
  • Vinaychandran Pondenkandath
  • Michele Alberti
  • Marcus Liwicki
  • Kaspar Riesen
  • Rolf Ingold
  • Andreas Fischer
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11004)


Biometric authentication by means of handwritten signatures is a challenging pattern recognition task, which aims to infer a writer model from only a handful of genuine signatures. In order to make it more difficult for a forger to attack the verification system, a promising strategy is to combine different writer models. In this work, we propose to complement a recent structural approach to offline signature verification based on graph edit distance with a statistical approach based on metric learning with deep neural networks. On the MCYT and GPDS benchmark datasets, we demonstrate that combining the structural and statistical models leads to significant improvements in performance, profiting from their complementary properties.


Offline signature verification Graph edit distance Metric learning Deep convolutional neural network Triplet network 



This work has been supported by the Swiss National Science Foundation project 200021_162852.


  1. 1.
    Alberti, M., Pondenkandath, V., Würsch, M., Ingold, R., Liwicki, M.: DeepDIVA: a highly-functional python framework for reproducible experiments. In: International Conference on Frontiers in Handwriting Recognition (2018, submitted)Google Scholar
  2. 2.
    Alonso-Fernandez, F., Fairhurst, M., Fierrez, J., Ortega-Garcia, J.: Automatic measures for predicting performance in off-line signature. In: Proceedings of the 14th International Conference on Image Processing, pp. 369–372 (2007)Google Scholar
  3. 3.
    Balntas, V., Riba, E., Ponsa, D., Mikolajczyk, K.: Learning local feature descriptors with triplets and shallow convolutional neural networks. In: Proceedings of the British Machine Vision Conference (BMVC), September 2016Google Scholar
  4. 4.
    Bansal, A., Gupta, B., Khandelwal, G., Chakraverty, S.: Offline signature verification using critical region matching. Int. J. Sig. Process. Image Process. Pattern Recogn. 2(1), 57–70 (2009)Google Scholar
  5. 5.
    Ferrer, M.A., Diaz-Cabrera, M., Morales, A.: Static signature synthesis: a neuromotor inspired approach for biometrics. IEEE Trans. Pattern Anal. Mach. Intell. 37(3), 667–680 (2015)CrossRefGoogle Scholar
  6. 6.
    Ferrer, M.A., Vargas, J.F., Morales, A., Ordonez, A.: Robustness of offline signature verification based on gray level features. IEEE Trans. Inf. Forensics Secur. 7(3), 966–977 (2012)CrossRefGoogle Scholar
  7. 7.
    Fierrez-Aguilar, J., Alonso-Hermira, N., Moreno-Marquez, G., Ortega-Garcia, J.: An off-line signature verification system based on fusion of local and global information. In: Maltoni, D., Jain, A.K. (eds.) BioAW 2004. LNCS, vol. 3087, pp. 295–306. Springer, Heidelberg (2004). Scholar
  8. 8.
    Fierrez-Aguilar, J., Ortega-Garcia, J., Gonzalez-Rodriguez, J.: Target dependent score normalization techniques and their application to signature verification. IEEE Trans. Syst. Man. Cybern. Part C 35(3), 418–425 (2004)CrossRefGoogle Scholar
  9. 9.
    Fotak, T., Baca, M., Koruga, P.: Handwritten signature identification using basic concepts of graph theory. WSEAS Trans. Sig. Process. 7(4), 145–157 (2011)Google Scholar
  10. 10.
    Gilperez, A., Alonso-Fernandez, F., Pecharroman, S., Fierrez, J., Ortega-Garcia, J.: Off-line signature verification using contour features. In: Proceedings of the 11th International Conference on Frontiers in Handwriting Recognition, pp. 1–6 (2008)Google Scholar
  11. 11.
    Hafemann, L.G., Sabourin, R., Oliveira, L.S.: Learning features for offline handwritten signature verification using deep convolutional neural networks. Pattern Recogn. 70, 163–176 (2017)CrossRefGoogle Scholar
  12. 12.
    Hafemann, L.G., Sabourin, R., Oliveira, L.S.: Offline handwritten signature verification - literature review. In: Proceedings of International Conference on Image Processing Theory, Tools and Applications (IPTA), pp. 1–8 (2017)Google Scholar
  13. 13.
    He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)Google Scholar
  14. 14.
    Hoffer, E., Ailon, N.: Deep metric learning using triplet network. In: Feragen, A., Pelillo, M., Loog, M. (eds.) SIMBAD 2015. LNCS, vol. 9370, pp. 84–92. Springer, Cham (2015). Scholar
  15. 15.
    Impedovo, D., Pirlo, G.: Automatic signature verification: the state of the art. IEEE Trans. Syst. Man Cybern. Part C 38(5), 609–635 (2008)CrossRefGoogle Scholar
  16. 16.
    Maergner, P., Riesen, K., Ingold, R., Fischer, A.: A structural approach to offline signature verification using graph edit distance. In: Proceedings of International Conference on Document Analysis and Recognition, pp. 1216–1222. IEEE (2017)Google Scholar
  17. 17.
    Malik, M.I., Liwicki, M.: From terminology to evaluation: performance assessment of automatic signature verification systems. In: Proceedings of International Conference on Frontiers in Handwriting Recognition, pp. 613–618 (2012)Google Scholar
  18. 18.
    Ortega-Garcia, J., et al.: MCYT baseline corpus: a bimodal biometric database. IEEE Proc.-Vis. Image Sig. Process. 150(6), 395–401 (2003)CrossRefGoogle Scholar
  19. 19.
    Plamondon, R., Lorette, G.: Automatic signature verification and writer identification - the state of the art. Pattern Recogn. 22(2), 107–131 (1989)CrossRefGoogle Scholar
  20. 20.
    Riesen, K., Bunke, H.: Approximate graph edit distance computation by means of bipartite graph matching. Image Vis. Comput. 27(7), 950–959 (2009)CrossRefGoogle Scholar
  21. 21.
    Riesen, K., Fischer, A., Bunke, H.: Computing upper and lower bounds of graph edit distance in cubic time. In: El Gayar, N., Schwenker, F., Suen, C. (eds.) ANNPR 2014. LNCS (LNAI), vol. 8774, pp. 129–140. Springer, Cham (2014). Scholar
  22. 22.
    Sabourin, R., Plamondon, R., Beaumier, L.: Structural interpretation of handwritten signature images. Int. J. Pattern Recog. Artif. Intell. 8(3), 709–748 (1994)CrossRefGoogle Scholar
  23. 23.
    Yilmaz, M.B., Yanikoglu, B., Tirkaz, C., Kholmatov, A.: Offline signature verification using classifier combination of HOG and LBP features. In: Proceedings of the International Joint Conference on Biometrics, pp. 1–7 (2011)Google Scholar
  24. 24.
    Zagoruyko, S., Komodakis, N.: Learning to compare image patches via convolutional neural networks. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 4353–4361 (2015)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  • Paul Maergner
    • 1
    Email author
  • Vinaychandran Pondenkandath
    • 1
  • Michele Alberti
    • 1
  • Marcus Liwicki
    • 1
  • Kaspar Riesen
    • 2
  • Rolf Ingold
    • 1
  • Andreas Fischer
    • 1
    • 3
  1. 1.DIVA GroupUniversity of FribourgFribourgSwitzerland
  2. 2.Institute for Information SystemsUniversity of Applied Sciences and Arts Northwestern SwitzerlandOltenSwitzerland
  3. 3.Institute of Complex SystemsUniversity of Applied Sciences and Arts Western SwitzerlandFribourgSwitzerland

Personalised recommendations