Evolutionary algorithm for selecting dynamic signatures partitioning approach

• Autorzy: Zalasiński Marcin , Laskowski Łukasz , Niksa-Rynkiewicz Tacjana , Cpałka Krzysztof , Byrski Aleksander , Przybyszewski Krzysztof , Trippner Paweł , Dong Shi

Identyfikatory

DOI

10.2478/jaiscr-2022-0018

• Języki publikacji: EN

Abstrakty

EN

In the verification of identity, the aim is to increase effectiveness and reduce involvement of verified users. A good compromise between these issues is ensured by dynamic signature verification. The dynamic signature is represented by signals describing the position of the stylus in time. They can be used to determine the velocity or acceleration signal. Values of these signals can be analyzed, interpreted, selected, and compared. In this paper, we propose an approach that: (a) uses an evolutionary algorithm to create signature partitions in the time and velocity domains; (b) selects the most characteristic partitions in terms of matching with reference signatures; and (c) works individually for each user, eliminating the need of using skilled forgeries. The proposed approach was tested using Biosecure DS2 database which is a part of the DeepSignDB, a database with genuine dynamic signatures. Our simulations confirmed the correctness of the adopted assumptions.

Słowa kluczowe

EN

identity verification; dynamic signature; hybrid partitions; partitions’ selection; evolutionary algorithm

• Wydawca: University of Social Sciences
• Czasopismo: Journal of Artificial Intelligence and Soft Computing Research
• Rocznik: 2022
• Tom: Vol. 12, No. 4
• Strony: 267--279
• Opis fizyczny: Bibliogr. 38 poz., rys.

Twórcy

autor

Zalasiński Marcin

• Częstochowa University of Technology, Department of Intelligent Computer Systems, Al. Armii Krajowej 36, 42-200 Częstochowa, Poland

autor

Laskowski Łukasz

• Polish Academy of Sciences, Institute of Nuclear Physics, Kraków, Poland

autor

Niksa-Rynkiewicz Tacjana

• Gdańsk University of Technology, Faculty of Ocean Engineering and Ship Technology, 11/12 Gabriela Narutowicza Street, 80-233 Gdańsk, Poland

autor

Cpałka Krzysztof

• Częstochowa University of Technology, Department of Intelligent Computer Systems, Al. Armii Krajowej 36, 42-200 Częstochowa, Poland

autor

Byrski Aleksander

• AGH University of Science and Technology, Institute of Computer Science, 30-059 Kraków, Poland

autor

Przybyszewski Krzysztof

• University of Social Sciences, Institute of Information Technologies, 9 Sienkiewicza Street, 90-113 Łódź, Poland

autor

Trippner Paweł

• University of Social Science, Management Department, 9 Sienkiewicza Street, 90–113 Łódź, Poland

autor

Dong Shi

• Zhoukou Normal University, School of Computer Science and Technology, China

Bibliografia

• [1] O. Alpar, Signature barcodes for online verification, Pattern Recognition, 124, 108426, 2022.
• [2] Ł. Bartczuk, A. Przybył, K. Cpałka, A new approach to nonlinear modelling of dynamic systems based on fuzzy rules, International Journal of Applied Mathematics and Computer Science (AMCS), 26(3), 603-621, 2016.
• [3] J. Bilski, B. Kowalczyk, A. Marchlewska, J.M. Zurada, Local Levenberg-Marquardt Algorithm for Learning Feedforwad Neural Networks, Journal of Artificial Intelligence and Soft Computing Research, 10(4), 299-316, 2020, https://doi.org/10.2478/jaiscr-2020-0020.
• [4] M. Chavan, R. R. Singh, V. A. Bharadi, Online Signature Verification Using Hybrid Wavelet Transform with Hidden Markov Model, International Conference on Computing, Communication, Control and Automation (ICCUBEA), 1-6, 2017, doi: 10.1109/iccubea.2017.8463660.
• [5] K. Cpałka, M. Zalasinski, On-line signature verification using vertical signature partitioning, Expert Systems with Applications, 41, 4170-4180, 2014.
• [6] K. Cpałka, M. Zalasinski, L. Rutkowski, New ´method for the on-line signature verification based on horizontal partitioning, Pattern Recognition, 47, 2652-2661, 2014.
• [7] K. Cpałka, M. Zalasinski, L. Rutkowski, A new algorithm for identity verification based on the analysis of a handwritten dynamic signature, Applied Soft Computing, 43, 47-56, 2016.
• [8] S. Das, P. N. Suganthan, Differential Evolution: A Survey of the State-of-the-Art, IEEE Transactions on Evolutionary Computation, 15, 4-31, 2011.
• [9] P. Duda, M. Jaworski, A. Cader, L. Wang, On Training Deep Neural Networks Using a Streaming Approach, Journal of Artificial Intelligence and Soft Computing Research, 10(1), 15-26, 2020, https://doi.org/10.2478/jaiscr-2020-0002.
• [10] P. Dziwinski, Ł. Bartczuk, J. Paszkowski, A new auto adaptive fuzzy hybrid particle swarm optimization and genetic algorithm, Journal of Artificial Intelligence and Soft Computing Research, 10(2), 95-111, 2020, https://doi.org/10.2478/jaiscr-2020-0007.
• [11] P. Dziwinski, P. Przybył, P. Trippner, J. Paszkowski, Y. Hayashi, hardware implementation of a Takagi-Sugeno neuro-fuzzy system optimized by a population algorithm, Journal of Artificial Intelligence and Soft Computing Research, 11(3), 243-266, 2021, https://doi.org/10.2478/jaiscr2021-0015.
• [12] J. Fierrez, J. Galbally, et al., BiosecurID: A Multimodal Biometric Database, Pattern Analysis and Applications, 13, 2, 235-246, 2010.
• [13] He, L., Tan, H. & Huang, ZC. Online handwritten signature verification based on association of curvature and torsion feature with Hausdorff distance. Multimed Tools Appl. 78, 19253-19278, 2019.
• [14] N. Houmani, A. Mayoue, S. Garcia-Salicetti, B. Dorizzi, M.I. Khalil, M.N. Moustafa, H. Abbas, D. Muramatsu, B. Yanikoglu, A. Kholmatov, M. Martinez-Diaz, J. Fierrez, J. OrtegaGarcia, J. Roure Alcobe, J. Fabregas, M. FaundezZanuy, J.M. Pascual-Gaspar, V. Cardenoso-Payo, Vivaracho-Pascual C., BioSecure signature evaluation campaign (BSEC’2009): Evaluating online signature algorithms depending on the quality of signatures, Pattern Recognition, 45, 993-1003, 2012.
• [15] H. Hu, J. Zheng, E. Zhan, J. Tang, Online signature verification based on a single template via elastic curve matching, Sensors, 19, 4858, 2019, https://doi.org/10.3390/s19224858.
• [16] M. Korytkowski, R. Senkerik, M.M. Scherer, R.A. Angryk, M. Kordos, A. Siwocha, Efficient Image Retrieval by Fuzzy Rules from Boosting and Metaheuristic, Journal of Artificial Intelligence and Soft Computing Research, 10(1), 57-69, 2020, https://doi.org/10.2478/jaiscr-2020-0005.
• [17] C. Li, X. Zhang, F. Lin, Z. Wang, L. Jun’E, R. Zhang, H. Wang, A stroke-based RNN for writerindependent online signature verification, In 2019 International Conference on Document Analysis and Recognition (ICDAR), IEEE, 526-532, 2019.
• [18] K. Łapa, K. Cpałka, A.I. Galushkin, A new interpretability criteria for neuro-fuzzy systems for nonlinear classification. In International Conference on Artificial Intelligence and Soft Computing, Springer, 448-468, 2015.
• [19] K. Łapa, K. Cpałka, Ł. Laskowski, A. Cader, Z. Zeng, Evolutionary Algorithm with a Configurable Search Mechanism, Journal of Artificial Intelligence and Soft Computing Research, 10(3), 151-171, 2020, https://doi.org/10.2478/jaiscr-2020-0011.
• [20] T. Niksa-Rynkiewicz, N. Szewczuk-Krypa, A. Witkowska, K. Cpałka, M. Zalasinski, A. Cader, Monitoring Regenerative Heat Exchanger in Steam Power Plant by Making Use of the Recurrent Neural Network, Journal of Artificial Intelligence and Soft Computing Research, 11(2), 143-155, 2021, https://doi.org/10.2478/jaiscr-2021-0009.
• [21] J. Ortega-Garcia, J. Fierrez, et al., The MultiScenario Multi-Environment BioSecure Multimodal Database (BMDB), IEEE Trans. on Pattern Analysis and Machine Intelligence, 32(6), 1097–1111, 2010.
• [22] J. Ortega-Garcia, J. Fierrez, et al., MCYT Baseline Corpus: A Bimodal Biometric Database, IEEE Proc. Vision, Image and Signal Processing, 150(6), 395-401, 2003.
• [23] M.E.H. Pedersen, Good parameters for differential evolution. Hvass Laboratories Technical Report, HL1002, 2010.
• [24] Y. Ren, C. Wang, Y. Chen, M. C. Chuah and J. Yang, Signature Verification Using Critical Segments for Securing Mobile Transactions, IEEE Transactions on Mobile Computing, 19(3), 724-739, 2020, doi: 10.1109/TMC.2019.2897657.
• [25] T. Rutkowski, K. Łapa, M. Jaworski, R. Nielek, D. Rutkowska, On explainable flexible fuzzy recommender and its performance evaluation using the Akaike information criterion, In International Conference on Neural Information Processing, Springer, 717-724, 2019.
• [26] J. Szczypta, A. Przybył, K. Cpałka, Some aspects of evolutionary designing optimal controllers, Artificial Intelligence and Soft Computing, Lecture Notes in Computer Science, 7895, Springer, 91-100, 2013.
• [27] K.S. Tang, K.F. Man, S. Kwong, Q. He, Genetic algorithms and their applications, IEEE Signal Processing Magazine, 13, 6, 1996.
• [28] R. Tolosana et al., SVC-onGoing: Signature verification competition, Pattern Recognition, 127, 108609, 2022, https://doi.org/10.1016/j.patcog.2022.108609.
• [29] R. Tolosana, R. Vera-Rodriguez, J. Fierrez, J. Ortega-Garcia, Exploring Recurrent Neural Networks for On-Line Handwritten Signature Biometrics, IEEE Access, 6, 5128-5138, 2018, doi: 10.1109/ACCESS.2018.2793966.
• [30] R. Tolosana, R. Vera-Rodriguez, J. Fierrez, and J. Ortega-Garcia, DeepSign: Deep On-Line Signature Verification, IEEE Transactions on Biometrics, Behavior, and Identity Science, 3(2), 229-239, 2021.
• [31] M. Zalasinski, K. Cpałka, A new method of on-line signature verification using a flexible fuzzy oneclass classifier, Academic Publishing House EXIT, 38-53, 2011.
• [32] M. Zalasinski, K. Cpałka, Novel algorithm for the on-line signature verification using selected discretization points groups, Artificial Intelligence and Soft Computing, Lecture Notes in Computer Science, 7894, Springer, 493-502, 2013.
• [33] M. Zalasinski, K. Cpałka, New Algorithm for On-line Signature Verification Using Characteristic Hybrid Partitions, Advances in Intelligent Systems and Computing, 432, Springer, 147-157, 2013.
• [34] M. Zalasinski, K. Cpałka, Y. Hayashi, New method for dynamic signature verification based on global features, Artificial Intelligence and Soft Computing, Lecture Notes in Computer Science, 8467, Springer, 251-265, 2014.
• [35] M. Zalasinski, K. Cpałka, Y. Hayashi, New fast algorithm for the dynamic signature verification using global features values, Artificial Intelligence and Soft Computing, Lecture Notes in Computer Science, 9120, Springer, 175-188, 2015.
• [36] M. Zalasinski, K. Cpałka, Ł. Laskowski, D.C. Wunsch, K. Przybyszewski, An Algorithm for the Evolutionary-Fuzzy Generation of on-Line Signature Hybrid Descriptors, Journal of Artificial Intelligence and Soft Computing Research, 10(3), 173-187, 2020, https://doi.org/10.2478/jaiscr-2020-0012.
• [37] M. Zalasinski, Krystian Łapa, K. Cpałka, New algorithm for evolutionary selection of the dynamic signature global features, Artificial Intelligence and Soft Computing, Lecture Notes in Computer Science, 7895, Springer, 113-121, 2013.
• [38] M. Zalasinski, K. Łapa, K. Cpałka, K. Przybyszewski, G.G. Yen, On-Line Signature Partitioning Using a Population Based Algorithm, Journal of Artificial Intelligence and Soft Computing Research, 10(1), 5-13, 2020, https://doi.org/10.2478/jaiscr-2020-0001.