SIGNATURE VERIFICATION AND RECOGNITION AS A MULTIPARAMETRIC PROCESS BASED ON A SPIKING NEURAL NETWORK
DOI:
https://doi.org/10.31649/1999-9941-2021-50-1-36-44Keywords:
online signature verification, spiking neural network, invariant dynamic parameters, signature recognition, biometrics, access controlAbstract
The article reviews the known methods of dynamic signature verification, which are summarized in the classification table. A method of dynamic signature verification based on a spiking neural network is proposed. Three dynamic parameters of the signature l(t), Dα(t), Z(t) are chosen, which are invariant to the angle of inclination of the signature, and after their normalization - also to the spatial and temporal scales of the signature. These dynamic signature parameters are simultaneously fed to the spiking neural network for recognition in the form of time series without prior conversion into a vector of static features. This, on the one hand, simplifies the method due to the absence of complex computational conversion procedures and, on the other hand, prevents the loss of useful information and therefore increases the accuracy and reliability of signature verification and recognition (especially for forgery signatures that are highly correlated with genuine ones). The used neural network has a simple learning procedure, and not all neurons of the network are trained, but only the output neurons. If you need to add new signatures, you do not need to retrain the entire network, but just add a few output neurons and learn only their connections.
References
I. M. El-Henawy, M. Z. Rashad, O. Nomir, and K. Ahmed, «Online Signature Verification: State of the art», International Journal of Computers & Technology, Volume 4, No. 2, March-April, 2013.
M. Diaz, M. A. Ferrer, D. Impedovo, M. I. Malik, G. Pirlo, and R. Plamondon, «A Perspective Analysis of Handwritten Signature Technology», ACM Comput. Surv., Vol. 51, No. 6, Article 117, January 2019.
T. Ju. Doroshenko, and E. Ju. Kostjuchenko, «Sistema autentifikacii na osnove dinamiki rukopisnoj podpisi», Doklady TUSUR, 2014, № 2(32), pp. 219-223.
Maged M. M. Fahmy, «Online handwritten signature verification system based on DWT features extraction and neural network classification», Ain Shams Engineering Journal, 2010, 1, pp. 59–70.
I. A. Sorokin, «Formirovanie sistemy priznakov dlja identifikacii lichnosti po dinamike vosproizvedenija podpisi», avtoref. dis. na soiskanie uch. stepeni kand. tehn. nauk, Penzenskij gos. un-t, Penza, 2005.
N. Houmani, and S. Garcia-Salicetti, «On hunting animals of the biometric menagerie for online signature», PLoS ONE, 11, 4, 2016.
S. V. Nаlwа, «Automatic On-Line Signature Verification», Рrосееdings оf thе IЕЕЕ, Vоl. 85, № 2, 1997.
V. Iranmanesh, S. M. S. Ahmad, W. A. W. Adnan, S. Yussof, O. A. Arigbabu, and F. L. Malallah, «Online Handwritten Signature Verification Using Neural Network Classifier Based on Principal Component Analysis», Hindawi Publishing Corporation, The Scientific World Journal, Volume 2014, Article ID 381469.
N. Houmani, S. Garcia-Salicetti, and B. Dorizzi, «On assessing the robustness of pen coordinates, pen pressure and pen inclination to time variability with personal entropy», In IEEE 3rd Int. Conf. on Biometrics: Theory, Applications, and Systems, 1–6, 2009.
S. A. Farimani, and M. V. Jahan, «An HMM for online signature verification based on velocity and hand movement directions», In 6th Iranian Joint Congress on Fuzzy and Intelligent Systems, 2018, pp. 205–209.
C. Gruber, T. Gruber, S. Krinninger, and B. Sick, «Online signature verification with support vector machines based on LCSS kernel functions», IEEE Transactions on Systems, Man, and Cybernetics Part B: Cybernetics, 40, 4, 2010, pp. 1088–1100.
A. McCabe, J. Trevathan, and W. Read, «Neural Network-based Handwritten Signature Verification», Journal of Computers, vol. 3, № 8, August 2008.
Weixin Yang, Lianwen Jin, and Manfei Liu, «Chinese character-level writer identification using path signature feature, dropstroke and deep CNN», In 2015 13th International Conference on Document Analysis and Recognition (ICDAR), pp. 546-550, IEEE, 2015.
R. Tolosana, R. Vera-Rodriguez, J. Fierrez, and J. Ortega-Garcia, «DeepSign: Deep On-Line Signature Verification», Preprint in IEEE Transactions on Biometrics Behavior and Identity Science, January 2021.
M. A. Aoun, and M. Boukadoum, «Learning algorithm and neurocomputing architecture for NDS Neurons», 2014 IEEE 13th International Conference on Cognitive Informatics and Cognitive Computing, London, UK, 2014, pp. 126-132.
M. M. Fard, M. M. Fard, and N. Mozayani, «A new on-line signature verification by Spatio-Temporal neural network», 2008 IEEE International Conference on Intelligence and Security Informatics, Taipei, Taiwan, 2008, pp. 233-235, doi: 10.1109/ISI.2008.4565065.
O. K. Kolesnytskyj, I. V. Bokotsey, and S. S. Yaremchuk, «Optoelectronic Implementation of Pulsed Neurons and Neural Networks Using Bispin-Devices», Optical Memory & Neural Networks (Information Optics), 2010, Vol. 19, № 2, рр. 154-165.
O. K. Kolesnytskyj, V. V. Kutsman, K. Skorupski, and M. Arshidinova, «Neurocomputer architecture based on spiking neural network and its optoelectronic implementation», Proc. SPIE 11176, Photonics Applications in Astronomy, Communications, Industry, and High-Energy Physics Experiments 2019, 1117609 (6 November 2019), doi: 10.1117/12.2536607.
W. Gerstner, and W. Kistler, Spiking Neuron Models: Single Neurons, Populations, Plasticity. Cambridge: Cambridge University Press, 2002, doi:10.1017/CBO9780511815706.
O. K. Kolesnytskij, and Samra Muavija Hassan Hamo, «Metod raspoznavanija mnogomernyh vremennyh rjadov pri pomoshhi impul'snyh nejronnyh setej», Іnformacіjnі tehnologії ta komp‘juterna іnzhenerіja, 2006, № 2(6), pp. 86-93.
W. Maass, «Networks of spiking neurons: the third generation of neural network models», Neural Networks, 10:1659-1671, 1997.
Downloads
-
PDF (Українська)
Downloads: 188
