DYNAMIC HANDWRITTEN SIGNATURE IDENTIFICATION USING SPIKING NEURAL NETWORK

Vladislav Kutsman

kutsmanvlad@gmail.com
1TOV "Ulf-Finans", Kyiv, Ukraine, 2 Vinnytsia National Technical University, Computer Sciences Department, Vinnytsia, Ukraine (Ukraine)
http://orcid.org/0000-0001-5256-9651

Oleh Kolesnytskyj


Vinnytsia National Technical University (Ukraine)
http://orcid.org/0000-0003-0336-4910

Abstract

The article proposes a method for dynamic signature identification based on a spiking neural network. Three dynamic signature parameters l(t), xy(t), p(t) are used, which are invariant to the signature slope angle, and after their normalization, also to the signature spatial and temporal scales. These dynamic parameters are fed to the spiking neural network for recognition simultaneously in the form of time series without preliminary transformation into a vector of static features, which, on the one hand, simplifies the method due to the absence of complex computational transformation procedures, and on the other hand, prevents the loss of useful information, and therefore increases the accuracy and reliability of signature identification and recognition (especially when recognizing forged signatures that are highly correlated with the genuine). The spiking neural network used has a simple training procedure, and not all neurons of the network are trained, but only the output ones. If it is necessary to add new signatures, it is not necessary to retrain the entire network as a whole, but it is enough to add several output neurons and learn only their connections. In the results of experimental studies of the software implementation of the proposed system, it’s EER = 3.9% was found when identifying skilled forgeries and EER = 0.17% when identifying random forgeries.


Keywords:

online signature identification, spiking neural network, invariant dynamic parameters, signature recognition

Al-Banhawy N. H., Mohsen H., Ghali N. I.: Signature identification and verification systems: a comparative study on the online and offline techniques. Future Computing and Informatics Journal 5(1), 2020, article 3 [https://digitalcommons.aaru.edu.jo/fcij/vol5/iss1/3]
  Google Scholar

Babita P.: Online Signature Recognition Using Neural Network. Journal of Electrical & Electronics 4(3), 2015, 1.
  Google Scholar

Diaz M., Ferrer M. A., Impedovo D., Malik M. I., Pirlo G., Plamondon R.: A Perspective Analysis of Handwritten Signature Technology. ACM Comput. Surv. 51(6), 2019, article 117.
DOI: https://doi.org/10.1145/3274658   Google Scholar

Doroshenko T. Y., Kostyuchenko E. Y: The authentication system based on dynamic handwritten signature. TUSUR 2(32), 2014, 219–223.
  Google Scholar

Fierrez J., Galbally J., et al.: BiosecurID: A Multimodal Biometric Database. Pattern Analysis and Applications 13(2), 2010, 235–246.
DOI: https://doi.org/10.1007/s10044-009-0151-4   Google Scholar

Fierrez J., Ortega-Garcia J., Ramos D., Gonzalez-Rodriguez J.: Hmm-Based On-Line Signature Verification: Feature Extraction And Signature Modeling. Pattern Recognition Letters 28(16), 2007, 2325–2334.
DOI: https://doi.org/10.1016/j.patrec.2007.07.012   Google Scholar

Gerstner W., Kistler W.: Spiking Neuron Models: Single Neurons, Populations, Plasticity. Cambridge University Press, Cambridge 2002. [http://doi.org/10.1017/CBO9780511815706].
DOI: https://doi.org/10.1017/CBO9780511815706   Google Scholar

Hamadly I., Khaleel A., Munim A., Hassan H. E., Mohamed H. K.: Online Signature Recognition And Verification Using (SURF) Algorithm With SVM Kernels. Journal of Al-Azhar University Engineering Sector 13(49), 2018, 1332–1344.
DOI: https://doi.org/10.21608/auej.2018.18939   Google Scholar

Houmani N., Garcia-Salicetti S., Dorizzi B.: On assessing the robustness of pen coordinates, pen pressure and pen inclination to time variability with personal entropy. IEEE 3rd Int. Conf. on Biometrics: Theory, Applications, and Systems 2009, 1–6.
DOI: https://doi.org/10.1109/BTAS.2009.5339074   Google Scholar

Kolesnytskij O. K., Samra Muavija Hassan Hamo: A method for recognizing multidimensional time series using pulsed neural networks. Information technology and computer engineering 2(6), 2006, 86–93.
  Google Scholar

Kolesnytskyj O. K., Bokotsey I. V., Yaremchuk S. S.: Optoelectronic Implementation of Pulsed Neurons and Neural Networks Using Bispin-Devices. Optical Memory & Neural Networks (Information Optics) 19(2), 2010, 154–165.
DOI: https://doi.org/10.3103/S1060992X10020062   Google Scholar

Kolesnytskyj O. K., Kutsman V. V., Skorupski K., Arshidinova M.: Neurocomputer architecture based on spiking neural network and its optoelectronic implementation. Proc. SPIE 11176, 2019, 1117609 [http://doi.org/10.1117/12.2536607].
DOI: https://doi.org/10.1117/12.2536607   Google Scholar

Kutsman V. V., Kolesnytskyj O. K., Denysov I. K.: Investigation of intrapersonal and interpersonal variability of dynamic signature parameters in the process of their identification, Optoelectronic Information-Power Technologies 39(2), 2020, 5–15.
DOI: https://doi.org/10.31649/1681-7893-2020-40-2-5-15   Google Scholar

Kutsman V. V., Kolesnytskyj O. K.: Signature verification and recognition as a multiparametric process based on a spiking neural network. Information technologies and computer engineering 50(1), 2021, 36–44 [http://doi.org/10.31649/1999-9941-2021-50-1-36-44].
DOI: https://doi.org/10.31649/1999-9941-2021-50-1-36-44   Google Scholar

Maass W.: Networks of spiking neurons: the third generation of neural network models. Neural Networks 10, 1997, 1659–1671.
DOI: https://doi.org/10.1016/S0893-6080(97)00011-7   Google Scholar

Nilchiyan M. R., Yusof R. B.: Improved Wavelet-Based Online Signature Verification Scheme Considering Pen Scenario Information. IEEE 1st International Conference on Artificial Intelligence, Modelling and Simulation 2013, 8–13.
DOI: https://doi.org/10.1109/AIMS.2013.10   Google Scholar

Ortega-Garcia J., Fierrez J., et al.: MCYT Baseline Corpus: A Bimodal Biometric Database. IEEE Proc. Vision, Image and Signal Processing 150(6), 2003, 395–401.
DOI: https://doi.org/10.1049/ip-vis:20031078   Google Scholar

Patil B. V., Patil P. R.: An Efficient DTW Algorithm For Online Signature Verification. IEEE International Conference on Advances in Communication and Computing Technology (ICACCT) 2018, 1–5.
DOI: https://doi.org/10.1109/ICACCT.2018.8529614   Google Scholar

Pavlidis I., Papanikolopoulos N. P., Mavuduru R.: Signature Identification Through The Use Of Deformable Structures. Signal Processing 71(2), 1998, 187–201.
DOI: https://doi.org/10.1016/S0165-1684(98)00144-3   Google Scholar

Tolosana R., Vera-Rodriguez R., Fierrez J., Ortega-Garcia J.: DeepSign: Deep On-Line Signature Verification. arXiv preprint arXiv: 2002.10119, 2020.
  Google Scholar

Vlachos M., Kollios G., Gunopulos D.: Discovering similar multidimensional trajectories. Proceedings 18th International Conference on Data Engineering 2002, 673–684.
  Google Scholar

Download


Published
2021-09-30

Cited by

Kutsman, V., & Kolesnytskyj, O. (2021). DYNAMIC HANDWRITTEN SIGNATURE IDENTIFICATION USING SPIKING NEURAL NETWORK. Informatyka, Automatyka, Pomiary W Gospodarce I Ochronie Środowiska, 11(3), 34–39. https://doi.org/10.35784/iapgos.2718

Authors

Vladislav Kutsman 
kutsmanvlad@gmail.com
1TOV "Ulf-Finans", Kyiv, Ukraine, 2 Vinnytsia National Technical University, Computer Sciences Department, Vinnytsia, Ukraine Ukraine
http://orcid.org/0000-0001-5256-9651

Authors

Oleh Kolesnytskyj 

Vinnytsia National Technical University Ukraine
http://orcid.org/0000-0003-0336-4910

Statistics

Abstract views: 277
PDF downloads: 145