Using Neural Network to Identify Forgery in Offline Signatures

  • Piyush Agrawal
  • Rahul Bhalsodia
  • Yash GargEmail author
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 1087)


This paper proposes an efficient method for the identification of forged signatures from offline handmade signatures. Signatures are majorly used as personal verification that can be abused by any unauthorized third party who would feign the identification of an individual which signifies the need for an automatic forgery identification system. Over a past few decades, there are significant attempts for the identification of forgery of signatures. Identification can be done either online- or offline-based mode. Offline mode works on the input image of a sign. We aim to purpose a technique for offline identification by using a simple shape based on geometrical features including area, center of gravity, eccentricity, kurtosis. Database of signatures is trained for two classes, genuine and forged. Two different classifiers, one based on SVM and other on artificial neural network (ANN), were used to identify and classify the signatures as genuine and forged.


Offline signature forgery Deep neural network Machine learning 


  1. 1.
    P. Arbelaez et al., Contour detection and hierarchical image segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 33(5), 898–916 (2011)CrossRefGoogle Scholar
  2. 2.
    A.S. Britto Jr., R. Sabourin, L.E. Oliveira, Dynamic selection of classifiers’a comprehensive review. Pattern Recogn. 47(11), 3665–3680 (2014)CrossRefGoogle Scholar
  3. 3.
    H. Federer, A note on the Gauss-Green theorem. Proc. Am. Math. Soc. 9(3), 447–451 (1958)MathSciNetCrossRefGoogle Scholar
  4. 4.
    J. Fierrez-Aguilar, N. Alonso-Hermira, G. Moreno-Marquez, J. Ortega-Garcia, An off-line signature verification system based on fusion of local and global information, in International Workshop on Biometric Authentication (Springer, Berlin, 2004), pp. 295–306CrossRefGoogle Scholar
  5. 5.
    Y. Guerbai, Y. Chibani, B. Hadjadji, The effective use of the one-class SVM classifier for handwritten signature verification based on writer-independent parameters. Pattern Recogn. 48(1), 103–113 (2015)CrossRefGoogle Scholar
  6. 6.
    L.G. Hafemann, R. Sabourin, L.S. Oliveira, Analyzing features learned for offline signature verification using deep CNNs, in 2016 23rd International Conference on Pattern Recognition (ICPR) (IEEE, New York, 2016), pp. 2989–2994Google Scholar
  7. 7.
    L.G. Hafemann, R. Sabourin, L.S. Oliveira, Writer-independent feature learning for offline signature verification using deep convolutional neural networks, in 2016 International Joint Conference on Neural Networks (IJCNN) (IEEE, New York, 2016), pp. 2576–2583Google Scholar
  8. 8.
    K. Huang, H. Yan, Off-line signature verification based on geometric feature extraction and neural network classification. Pattern Recogn. 30(1), 9–17 (1997)CrossRefGoogle Scholar
  9. 9.
    D. Impedovo, G. Pirlo, Automatic signature verification: The state of the art. IEEE Trans. Syst. Man, Cybern., Part C (Appl. Rev.) 38(5), 609–635 (2008)CrossRefGoogle Scholar
  10. 10.
    D. Impedovo, G. Pirlo, R. Plamondon, Handwritten signature verification: New advancements and open issues, in 2012 International Conference on Frontiers in Handwriting Recognition (ICFHR) (IEEE, New York, 2012), pp. 367–372Google Scholar
  11. 11.
    M.K. Kalera, S. Srihari, A. Xu, Offline signature verification and identification using distance statistics. Int. J. Pattern Recogn. Artif. Intell. 18(07), 1339–1360 (2004)CrossRefGoogle Scholar
  12. 12.
    R. Kumar, L. Kundu, B. Chanda, J. Sharma, A writer-independent off-line signature verification system based on signature morphology, in Proceedings of the First International Conference on Intelligent Interactive Technologies and Multimedia (ACM, New York, 2010), pp. 261–265Google Scholar
  13. 13.
    F. Leclerc, R. Plamondon, Automatic signature verification: The state of the art 1989–1993. Int. J. Pattern Recogn. Artif. Intell. 8(03), 643–660 (1994)CrossRefGoogle Scholar
  14. 14.
    L.S. Oliveira, E. Justino, C. Freitas, R. Sabourin, The graphology applied to signature verification, in 12th Conference of the International Graphonomics Society (2005), pp. 286–290Google Scholar
  15. 15.
    R. Plamondon, G. Lorette, Automatic signature verification and writer identification-the state of the art. Pattern Recogn. 22(2), 107–131 (1989)CrossRefGoogle Scholar
  16. 16.
    R. Sabourin, J.P. Drouhard, Off-line signature verification using directional pdf and neural networks, in Proceedings of 11th IAPR International Conference on Pattern Recognition 1992, vol. II. Conference B: Pattern Recognition Methodology and Systems (IEEE, New York, 1992), pp. 321–325Google Scholar
  17. 17.
    R. Sabourin, G. Genest, An extended-shadow-code based approach for off-line signature verification. I. Evaluation of the bar mask definition, in Proceedings of the 12th IAPR International Conference on Pattern Recognition 1994, Conference B: Computer Vision & Image Processing, vol. 2 (IEEE, New York, 1994), pp. 450–453Google Scholar
  18. 18.
    Y. Serdouk, H. Nemmour, Y. Chibani, Combination of OC-LBP and longest run features for off-line signature verification, in 2014 Tenth International Conference on Signal-Image Technology and Internet-Based Systems (SITIS) (IEEE, New York, 2014), pp. 84–88Google Scholar
  19. 19.
    A. Soleimani, B.N. Araabi, K. Fouladi, Deep multitask metric learning for offline signature verification. Pattern Recogn. Lett. 80, 84–90 (2016)CrossRefGoogle Scholar
  20. 20.
    M.H.J. Vala, A. Baxi, A review on Otsu image segmentation algorithm. Int. J. Adv. Res. Comput. Eng. Technol. (IJARCET) 2(2), 387 (2013)Google Scholar
  21. 21.
    Z. Zhang, X. Liu, Y. Cui, Multi-phase offline signature verification system using deep convolutional generative adversarial networks, in 2016 9th International Symposium on Computational Intelligence and Design (ISCID), vol. 2 (IEEE, New York, 2016), pp. 103–107Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2020

Authors and Affiliations

  1. 1.Bharati Vidyapeeth’s College of EngineeringNew DelhiIndia

Personalised recommendations