Offline Handwritten Signature Authentication with Conditional Deep Convolutional Generative Adversarial Networks

  • David C. Yonekura UEA
  • Elloá B. Guedes UEA


Handwritten signature authentication systems are important in many real world scenarios to avoid frauds. Thanks to Deep Learning, state-of-art solutions have been proposed to this problem by making use of Convolutional Neural Networks, but other models in this Machine Learning subarea are still to be further explored. In this perspective, the present article introduces a Conditional Deep Convolutional Generative Adversarial Networks (cDCGAN) approach whose experimental results in a realistic dataset with skilled forgeries have Equal Error Rate (EER) of 18.53% and balanced accuracy of 87.91%. These results validate a writerdependent cDCGAN-based solution to the signature authentication problem in a real world scenario where no forgeries are available nor required in training time.


Andress, J. (2014). The Basics of Information Security – Understanding the Fundamentals of InfoSec in Theory and Practice. Elsevier, Oxford, UK.

Araújo, M. W. V. (2019). Verificação da autenticidade de assinaturas manuscritas utilizando redes neurais convolucionais. Trabalho de Conclusão de Curso de Bacharelado em Engenharia de Computação na Universidade do Estado do Amazonas.

Berthelot, D., Schumm, T., and Metz, L. (2017). Began: Boundary equilibrium generative adversarial networks. arXiv preprint arXiv:1703.10717.

Blankers, V. L., van den Heuvel, C. E., Franke, K. Y., and Vuurpijl, L. G. (2009). The icdar In 10th International Conference on Document 2009 signature verification competition. Analysis and Recognition, pages 1403–1407, Barcelona, Catalonia, Spain. IEEE.

Ferrer, M. A., Diaz-Cabrera, M., and Morales, A. (2013). Synthetic off-line signature image generation. In 2013 International Conference on Biometrics (ICB), pages 1–7, Espanha.

Foster, D. (2019). Generative Deep Learning: Teaching Machines to Paint, Write, Compose, and Play. O’Reilly Media, United Kingdom.

Ganguly, K. (2017). Learning Generative Adversarial Networks. Packt Publishing, United Kingdom.

Goodfellow, I., Bengio, Y., and Courville, A. (2016). Deep Learning, volume 1. The MIT Press, Cambridge.

Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., and Bengio, Y. (2014). Generative adversarial nets. In Ghahramani, Z., Welling, M., Cortes, C., Lawrence, N., and Weinberger, K. Q., editors, Advances in Neural Information Processing Systems, volume 27, pages 2672–2680, Barcelona. Curran Associates, Inc.

Hafemann, L. G., Sabourin, R., and Oliveira, L. S. (2017a). Learning features for ofine handwritten signature verification using deep convolutional neural networks. Pattern Recognition, 70:163–176.

Hafemann, L. G., Sabourin, R., and Oliveira, L. S. (2017b). Ofine handwritten signature verification literature review. In 2017 Seventh International Conference on Image Processing Theory, Tools and Applications (IPTA), pages 1–8, Canada. IEEE.

Hameed, M. M., Ahmad, R., Kiah, M. L. M., and Murtaza, G. (2021). Machine learningbased ofine signature verification systems: A systematic review. Signal Processing: Image Communication, 93:116139.

Hand, D. J. (2009). Measuring classifier performance: a coherent alternative to the area under the ROC curve. Machine Learning, 77(1):103–123.

Heinen, M. R. (2002). Autenticação on-line de assinaturas utilizando redes neurais.

Impedovo, D. and Pirlo, G. (2008). Automatic signature verification: The state of the art. IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews), 38:609–635.

Kalera, M. K., Srihari, S., and Xu, A. (2004). Ofine signature verification and identification using distance statistics. International Journal of Pattern Recognition and Artificial Intelligence, 18(07):1339–1360.

Khan, S., Rahmani, H., Shah, S. A. A., and Bennamoun, M. (2018). A Guide to Convolutional Neural Networks for Computer Vision. Morgan and Claypool.

Langr, J. and Bok, V. (2019). Generative Adversarial Networks in Action – Deep Learning with Generative Adversarial Networks. Manning Publications, Shelter Island.

Mirza, M. and Osindero, S. (2014). Conditional generative adversarial nets. arXiv preprint arXiv:1411.1784.

Ortega-Garcia, J., Fierrez-Aguilar, J., Simon, D., Gonzalez, J., Faundez-Zanuy, M., Espinosa, V., Satue, A., Hernaez, I., Igarza, J.-J., Vivaracho, C., Escudero, D., and Moro, Q.-I. (2003). MCYT baseline corpus: a bimodal biometric database. IEE Proceedings Vision, Image, and Signal Processing, 150(6):395.

Radford, A., Metz, L., and Soumith, C. (2016). Unsupervised representation learning with In 6th International Conference on deep convolutional generative adversarial networks. Learning Representations, page 16, Puerto Rico.

Sanmorino, A. and Yazid, S. (2012). A survey for handwritten signature verification. In 2012 2nd International Conference on Uncertainty Reasoning and Knowledge Engineering, pages 54–57, Jalarta. IEEE.

Wang, S. and Jia, S. (2019). Signature handwriting identification based on generative adversarial networks. Journal of Physics: Conference Series, 1187(4):042047.

Wayman, J., Jain, A., Maltoni, D., and Maio, D. (2005). An introduction to biometric authentication systems. In Biometric Systems, pages 1–20. Springer-Verlag.

Yapc, M. M., Tekerek, A., and Topaloglu, N. (2020). Deep learning-based data augmentation method and signature verification system for ofine handwritten signature. Pattern Analysis and Applications, 24(1):165–179.

Zhang, Z., Liu, X., and Cui, Y. (2016). Multi-phase ofine signature verification system using deep convolutional generative adversarial networks. In 2016 9th International Symposium on Computational Intelligence and Design (ISCID). IEEE.
Como Citar

Selecione um Formato
YONEKURA, David C.; GUEDES, Elloá B.. Offline Handwritten Signature Authentication with Conditional Deep Convolutional Generative Adversarial Networks. In: ENCONTRO NACIONAL DE INTELIGÊNCIA ARTIFICIAL E COMPUTACIONAL (ENIAC), 18. , 2021, Evento Online. Anais [...]. Porto Alegre: Sociedade Brasileira de Computação, 2021 . p. 482-491. ISSN 2763-9061. DOI: