Использование методов глубокого обучения для верификации подписей

F B Albasu; M A Al Akkad

doi:10.22213/2410-9304-2023-3-27-39

Authors

F. B. Albasu Kalashnikov Izhevsk State Technical University
M. A. Al Akkad Kalashnikov Izhevsk State Technical University

DOI:

https://doi.org/10.22213/2410-9304-2023-3-27-39

Keywords:

deep learning, authentication, signature verification, pattern recognition, biometric identification

Abstract

Biometric featuresare common measures of identity verification where signaturesarethe most used type. The digital technology has given birth to new ways of biometric identification, such as fingerprints, iris and face recognition,while dealing with handwritten signatures is still a challenging task, because handwritten signatures are more prone to forgery than other means of verification due to issues like computer error, insufficient datasets, and loss of information. This work aims to develop a system that takes a signature image as its input and determines whether the signature is genuine written by its author or forged by another individual. The system is based on a neural network algorithm called Convolutional Siamese Neural Networks, which is used for deep learning and computer vision as well as other machine learning tasks such as natural language processing and digital signal processing.A Contrastive Loss function which compares the Euclidean distance of the output feature vectors is used, and a writer-independent model is used for training and image classification. This work’s objective is toenhance the precision of signature verification and take it as a base for future work on signature verification and use it in user identification, fraud detection and prevention, and forensic investigation applications. The system can be applied in banking, government and private organizations, and forensic investigation for identity and document verification, impersonation and fraud detection and prevention, crime and judicial investigation, and passport verification

Author Biographies

F. B. Albasu, Kalashnikov Izhevsk State Technical University

Studen

M. A. Al Akkad, Kalashnikov Izhevsk State Technical University

PhD in Engineering, Associate Professor

References

Sarker, I. H. (2021). Machine Learning: Algorithms, Real-World Applications and Research Directions. SN Computer Science, vol. 2, no. 3, p. 160. Springer Link. URL: https://doi.org/10.1007/s42979-021-00592-x.

Masoudnia, S., et al. (2019). Multi-Representational Learning for Offline Signature Verification Using Multi-Loss Snapshot Ensemble of CNNs. Expert Systems with Applications, vol. 133, pp. 317-30. arXiv.org. URL: https://doi.org/10.1016/j.eswa.2019.03.040.

Ansari, A., et al. (2014). Online signature verification using segment-level fuzzy modeling. IET biometrics,vol. 3, no. 3, pp. 113-127.

Sandipan, D. (2018). Hands-on Image Processing with Python: Expert Techniques for Advanced Image Analysis and Effective Interpretation of Image Data. Packt Publishing. Open WorldCat. URL: http://proquestcombo.safaribooksonline.com/9781789343731.

Manohar, S. (2017). Mastering Machine Learning with Python in Six Steps: A Practical Implementation Guide to Predictive Data Analytics Using Python. Apress.

Vinushanth, C. V. (2020). Markov and Hidden Markov Model. Medium. URL: https://towardsdatascience.com/markov-and-hidden-markov-model-3eec42298d75.

Bertolini, D., et al. (2010). Reducing Forgeries in Writer-Independent off-Line Signature Verification through Ensemble of Classifiers. Pattern Recognition, vol. 43, no. 1, pp. 387-96. URL: https://doi.org/10.1016/j.patcog.2009.05.009.

Bindal, A. (2019). Normalization Techniques in Deep Neural Networks. Techspace. URL: https://medium.com/techspace-usict/normalization-techniques-in-deep-neural-networks-9121bf100d8.

Kang, N. (2019).Introducing Deep Learning and Neural Networks - Deep Learning for Rookies (1). Medium. URL: https://towardsdatascience.com/introducing-deep-learning-and-neural-networks-deep-learning-for-rookies-1-bd68f9cf5883.

Sanghvirajit. (2021). A Complete Guide to Adam and RMSprop Optimizer.Analytics Vidhya. URL: https://medium.com/analytics-vidhya/a-complete-guide-to-adam-and-rmsprop-optimizer-75f4502d83be.

Kingma, D. P., and Ba, J.(2017). Adam: A Method for Stochastic Optimization. arXiv:1412.6980. URL: http://arxiv.org/abs/1412.6980.

Benhur, S. J. (2021). A Friendly Introduction to Siamese Networks. Medium. URL: https://towardsdatascience.com/a-friendly-introduction-to-siamese-networks-85ab17522942.

Shah, A., et al. (2016). An Offline Signature Verification Technique Using Pixels Intensity Levels.International Journal of Signal Processing, Image Processing and Pattern Recognition, vol. 9, no. 8, pp. 205-22. URL: https://doi.org/10.14257/ijsip.2016.9.8.18.

Odeh, S., and Khalil, M.(2011). Apply Multi-Layer Perceptrons Neural Network for Off-Line Signature Verification and Recognition.International Journal of Computer Science Issues (IJCSI),vol. 8, no. 6, pp. 261-266.

Madasu, Vamsi K., et al. Automatic Handwritten Signature Verification System for Australian Passports. Science, Engineering and Technology Summit on Counter-Terrorism Technology, pp. 53-66.

Hadsell, R., et al. (2006). Dimensionality Reduction by Learning an Invariant Mapping. IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06), vol. 2, pp. 1735-1742. https://doi.org/10.1109/CVPR.2006.100.

Hafemann, L. G., et al. (2018). Fixed-Sized Representation Learning from Offline Handwritten Signatures of Different Sizes.International Journal on Document Analysis and Recognition (IJDAR), vol. 21, no. 3, pp. 219-32. arXiv.org. URL: https://doi.org/10.1007/s10032-018-0301-6.

Krizhevsky, A., et al. (2017). ImageNet Classification with Deep Convolutional Neural Networks.Communications of the ACM, vol. 60, no. 6, pp. 84-90. URL: https://doi.org/10.1145/3065386.

Hafemann, L. G., et al. (2017). Learning Features for Offline Handwritten Signature Verification Using Deep Convolutional Neural Networks. Pattern Recognition, vol. 70, pp. 163-176. arXiv.orgю URL: https://doi.org/10.1016/j.patcog.2017.05.012.

Justino, E. J. R., et al. (2001). Off-Line Signature Verification Using HMM for Random, Simple and Skilled Forgeries. Proceedings of Sixth International Conference on Document Analysis and Recognition, IEEE Comput. Soc, pp. 1031-1034. URL: https://doi.org/10.1109/ICDAR.2001.953942.

Pal, S., et al. (2011). Off-Line Signature Verification Systems: A Survey. Proceedings of the International Conference & Workshop on Emerging Trends in Technology - ICWET'11, ACM Press, pp. 652-657. URL: https://doi.org/10.1145/1980022.1980163.

Karouni, A., et al. (2011). Offline Signature Recognition Using Neural Networks Approach. Procedia Computer Science, vol. 3, pp. 155-61. URL: https://doi.org/10.1016/j.procs.2010.12.027.

Koch, G., et al. (2015). Siamese Neural Networks for One-Shot Image Recognition. ICML deep learning workshop, vol. 2.

Dey, S., et al. (2017). SigNet: Convolutional Siamese Network for Writer Independent Offline Signature Verification. arXiv:1707.02131ю URL: http://arxiv.org/abs/1707.02131.

Sangekar, S. S., and Dhanwani D. C. (2012).Survey of Various Techniques for Signature Recognition and Verification.International Journal of Science and Research (IJSR), vol. 3,no. 11, pp. 1520-1522.

Oliveira, L. S., et al. The Graphology Applied to Signature Veri cation. 12th Conf.Int. Graphonomics Soc. (IGS2005), pp. 286-290.

Hafemann, L. G., et al. (2016). Writer-Independent Feature Learning for Offline Signature Verification Using Deep Convolutional Neural Networks.International Joint Conference on Neural Networks (IJCNN), pp. 2576-83. arXiv.orgю URL: https://doi.org/10.1109/IJCNN.2016.7727521.

Saha, S.(2018). A Comprehensive Guide to Convolutional Neural Networks - the ELI5 Way. Mediumю URL: https://towardsdatascience.com/a-comprehensive-guide-to-convolutional-neural-networks-the-eli5-way-3bd2b1164a53.

Farimani, S. A., and Majid V. J. (2018). An HMM for Online Signature Verification Based on Velocity and Hand Movement Directions. 6th Iranian Joint Congress on Fuzzy and Intelligent Systems (CFIS), pp. 205-09. IEEE Xploreю URL: https://doi.org/10.1109/CFIS.2018.8336639.

Chavan, M., et al. (2017). Handwritten Signature Verification Using Hidden Markov Model with Hybrid Wavelet Transform.International Conference on Computing, Communication, Control and Automation (ICCUBEA), pp. 1-6. IEEE Xploreю URL: https://doi.org/10.1109/ICCUBEA.2017.8463675.

Frias-Martinez, E., et al. (2006). Support Vector Machines versus Multi-Layer Perceptrons for Efficient off-Line Signature Recognition. Engineering Applications of Artificial Intelligence, vol. 19, no. 6, pp. 693-704. URL: https://doi.org/10.1016/j.engappai.2005.12.006.

Faúndez-Zanuy, M. (2007). On-Line Signature Recognition Based on VQ-DTW. Pattern Recognition, vol. 40, no. 3, pp. 981-992. URL: https://doi.org/10.1016/j.patcog.2006.06.007.

Justino, E. J. R., et al. (2002). An Off-Line Signature Verification System Using HMM and Graphometric Features. 4th IAPR International Workshop on Document Analysis Systemsp. pp. 211-222.

Alvarez, G., et al. (2016). Of ine Signature Veri cation with Convolutional Neural Networks. Technical report, Stanford University.

Yılmaz, M. B., and Berrin Y. (2016) Score Level Fusion of Classifiers in Off-Line Signature Verification.Information Fusion, vol. 32, pp. 109-19. URL: https://doi.org/10.1016/j.inffus.2016.02.003.

Eskander, G. S., et al. (2013). Hybrid Writer-independent-Writer-dependent Offline Signature Verification System. IET Biometrics, vol. 2, no. 4, pp. 169-181. URL: https://doi.org/10.1049/iet-bmt.2013.0024.

Zhang, Z., et al. (2016). Multi-Phase Offline Signature Verification System Using Deep Convolutional Generative Adversarial Networks.9th International Symposium on Computational Intelligence and Design (ISCID), vol. 2, pp. 103-107. IEEE Xploreю URL: https://doi.org/10.1109/ISCID.2016.2033.

Donato, I. and Pirlo, G. (2008). Automatic Signature Verification: The State of the Art. IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews), vol. 38, no. 5, pp. 609-35. URL: https://doi.org/10.1109/TSMCC.2008.923866.

Ippolito, P. P. (2019). Feature Extraction Techniques. Mediumю URL: https://towardsdatascience.com/feature-extraction-techniques-d619b56e31be.

Anamika, J., et al. (2021). Signature Verification Using Geometrical Features and Artificial Neural Network Classifier. Neural Computing and Applications, vol. 33, no. 12, pp. 6999-7010. arXiv.org. URL: https://doi.org/10.1007/s00521-020-05473-7.

Alaei, A., et al. (2017). An Efficient Signature Verification Method Based on an Interval Symbolic Representation and a Fuzzy Similarity Measure. IEEE Transactions on Information Forensics and Security, vol. 12, no. 10, pp. 2360-2372. URL: https://doi.org/10.1109/TIFS.2017.2707332.

Alajrami, E., et al. (2020). Handwritten Signature Verification Using Deep Learning.International Journal of Academic Multidisciplinary Research (IJAMR), vol. 3, тo. 12, pp. 39-44.

Arathi, M., and Govardhan, A.(2014). An Efficient Offline Signature Verification System.International Journal of Machine Learning and Computing, vol. 4, no. 6, pp. 533-537. URL: https://doi.org/10.7763/IJMLC.2014.V6.468.

Khalil, M. I., et al. (2009). Enhanced DTW Based On-Line Signature Verification. 16th IEEE International Conference on Image Processing (ICIP), IEEE, pp. 2713-2716. URL: https://doi.org/10.1109/ICIP.2009.5414166.

Hafemann, L. G., et al. (2017). Offline Handwritten Signature Verification - Literature Review. Seventh International Conference on Image Processing Theory, Tools and Applications (IPTA), IEEE, pp. 1-8. URL: https://doi.org/10.1109/IPTA.2017.8310112.