An Architecture Based on Capsule Networks for the Identification of Handwritten Signature Forgery

Authors: Luisa Mesquita Oliveira Ribeiro, Alexei Manso Correa Machado

Abstract:

Handwritten signature is a unique form for recognizing an individual, used to discern documents, carry out investigations in the criminal, legal, banking areas and other applications. Signature verification is based on large amounts of biometric data, as they are simple and easy to acquire, among other characteristics. Given this scenario, signature forgery is a worldwide recurring problem and fast and precise techniques are needed to prevent crimes of this nature from occurring. This article carried out a study on the efficiency of the Capsule Network in analyzing and recognizing signatures. The chosen architecture achieved an accuracy of 98.11% and 80.15% for the CEDAR and GPDS databases, respectively.

Keywords: Biometrics, deep learning, handwriting, signature forgery.

References:

[1] E. A. Soelistio, R. E. Hananto Kusumo, Z. V. Martan, and E. Irwansyah, “A review of signature recognition using machine learning,” in 2021 1st International Conference on Computer Science and Artificial Intelligence (ICCSAI), vol. 1, 2021, pp. 219–223.
[2] S. Sabour, N. Frosst, and G. E. Hinton, “Dynamic routing between capsules,” ArXiv, vol. abs/1710.09829, p. 3859–3869, 2017.
[3] S. Srihari, S.-H. Cha, H. Arora, and S. Lee, “Individuality of handwriting,” Journal of forensic sciences, vol. 47, pp. 856–72, 08 2002.
[4] M. A. Ferrer, M. Diaz, C. Carmona-Duarte, and A. Morales, “A behavioral handwriting model for static and dynamic signature synthesis,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 39, no. 6, pp. 1041–1053, 2017.
[5] V. L. F. Souza, A. L. I. Oliveira, and R. Sabourin, “A writer-independent approach for offline signature verification using deep convolutional neural networks features,” in 2018 7th Brazilian Conference on Intelligent Systems (BRACIS), 2018, pp. 212–217.
[6] D. Gumusbas and T. Yildirim, “Offline signature identification and verification using capsule network,” in 2019 IEEE International Symposium on INnovations in Intelligent SysTems and Applications (INISTA), 2019.
[7] N. Arab, H. Nemmour, and Y. Chibani, “New local difference feature for off-line handwritten signature verification,” in 2019 International Conference on Advanced Electrical Engineering (ICAEE), 2019, pp. 1–5.
[8] ——, “Improved multi-scale local difference features for off-line handwritten signature verification,” in 2020 1st International Conference on Communications, Control Systems and Signal Processing (CCSSP), 2020, pp. 266–270.
[9] ——, “Multiscale fusion of histogram-based features for robust off-line handwritten signature verification,” in 2020 IEEE/ACS 17th International Conference on Computer Systems and Applications (AICCSA), 2020, pp. 1–5.
[10] S. V. Bonde, P. Narwade, and R. Sawant, “Offline signature verification using convolutional neural network,” in 2020 6th International Conference on Signal Processing and Communication (ICSC), 2020, pp. 119–127.
[11] Z. Mohammad, I. Jahan, M. M. Kabir, M. A. Ali, and M. Mridha, “An offline writer-independent signature verification system using autoembedder,” in 2021 24th International Conference on Computer and Information Technology (ICCIT), 2021, pp. 1–6.
[12] W. Xiao and D. Wu, “An improved siamese network model for handwritten signature verification,” in 2021 IEEE International Conference on Networking, Sensing and Control (ICNSC), 2021, pp. 1–6.
[13] H. Li, P. Wei, and P. Hu, “Avn: An adversarial variation network model for handwritten signature verification,” IEEE Transactions on Multimedia, pp. 594–608, 2022.
[14] Y. Lecun, L. Bottou, Y. Bengio, and P. Haffner, “Gradient-based learning applied to document recognition,” Proceedings of the IEEE, vol. 86, no. 11, pp. 2278–2324, 1998.
[15] S. Sabour, N. Frosst, and G. E. Hinton, “Dynamic routing between capsules,” CoRR, vol. abs/1710.09829, 2017.
[Online]. Available: http://arxiv.org/abs/1710.09829