Vanilla convolutional neural network is all you need for online and offline signature verification

• Autorzy: Yilmaz Mustafa Berkay , Öztürk Kağan

Identyfikatory

DOI

10.61822/amcs-2025-0025

• Języki publikacji: EN

Abstrakty

EN

Recent advances in deep learning have been utilized successively to improve the performance of signature verification (SV) systems. Deep models proposed in the literature are complicated and need to learn many parameters to give acceptable error rates, requiring a lot of training data. On the other hand, those models are designed and hand-crafted specializing in the problem, online or offline SV. In this work, we suggest and show on popular datasets that similar and simple convolutional neural network (CNN) models can achieve state-of-the-art results both for offline and online SV problems. For offline SV, our work outperforms its counterparts with and without data augmentation. We also show that a very similar CNN architecture can be employed for online SV. To the best of our knowledge, this is the first work to show that CNNs can be used to learn online signature representations directly from raw data.

Słowa kluczowe

EN

signature verification; representation learning; deep learning; convolutional neural network

PL

weryfikacja podpisu; uczenie głębokie; sieć neuronowa konwolucyjna

• Wydawca: Oficyna Wydawnicza Uniwersytetu Zielonogórskiego
• Czasopismo: International Journal of Applied Mathematics and Computer Science
• Rocznik: 2025
• Tom: Vol. 35, no. 2
• Strony: 357--370
• Opis fizyczny: Bibliogr. 59 poz., rys., tab.

Twórcy

autor

Yilmaz Mustafa Berkay

• Department of Computer Engineering, Akdeniz University, Dumlupınar Boulevard, 07058 Konyaaltı, Antalya, Turkey

autor

Öztürk Kağan

• Department of Computer Science and Engineering, University of Notre Dame, Holy Cross Drive 384, 46556 Notre Dame, Indiana, USA

Bibliografia

• [1] Ahrabian, K. and BabaAli, B. (2019). Usage of autoencoders and siamese networks for online handwritten signature verification, Neural Computing and Applications 31(12): 9321-9334.
• [2] Arab, N., Nemmour, H. and Chibani, Y. (2023). A new synthetic feature generation scheme based on artificial immune systems for robust offline signature verification, Expert Systems with Applications 213(Part C): 119306.
• [3] Avola, D., Bigdello, M.J., Cinque, L., Fagioli, A. and Marini, M.R. (2021). R-sigNet: Reduced space writer-independent feature learning for offline writer-dependent signature verification, Pattern Recognition Letters 150(C): 189-196.
• [4] Bromley, J., Guyon, I., LeCun, Y., Säckinger, E. and Shah, R. (1994). Signature verification using a “siamese” time delay neural network, in J. Cowan et al. (Eds), Advances in Neural Information Processing Systems, Morgan Kaufmann, San Francisco, USA, pp. 737-744.
• [5] Calik, N., Kurban, O.C., Yilmaz, A.R., Yildirim, T. and Ata, L.D. (2019). Large-scale offline signature recognition via deep neural networks and feature embedding, Neurocomputing 359(C): 1-14.
• [6] Devidas, S., Rao, Y.S. and Rekha, N.R. (2021). A decentralized group signature scheme for privacy protection in a blockchain, International Journal of Applied Mathematics and Computer Science 31(2): 353-364, DOI: 10.34768/amcs-2021-0024.
• [7] Dey, S., Dutta, A., Toledo, J.I., Ghosh, S.K., Lladós, J. and Pal, U. (2017). SigNet: Convolutional siamese network for writer independent offline signature verification, arXiv: 1707.02131.
• [8] Diaz, M., Ferrer, M.A., Impedovo, D., Malik, M.I., Pirlo, G. and Plamondon, R. (2019). A perspective analysis of handwritten signature technology, ACM Computing Surveys 51(6): 1-39.
• [9] Ferrer, M.A., Diaz, M., Carmona-Duarte, C. and Morales, A. (2016). A behavioral handwriting model for static and dynamic signature synthesis, IEEE Transactions on Pattern Analysis and Machine Intelligence 39(6): 1041-1053.
• [10] Fierrez, J., Ortega-Garcia, J., Ramos, D. and Gonzalez-Rodriguez, J. (2007). HMM-based on-line signature verification: Feature extraction and signature modeling, Pattern Recognition Letters 28(16): 2325-2334.
• [11] Giazitzis, A. and Zois, E. (2024). SigmML: Metric meta-learning for writer independent offline signature verification in the space of SPD matrices, 2024 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Waikoloa, Hawaii, United States, pp. 6300-6310.
• [12] Hafemann, L.G., Oliveira, L.S. and Sabourin, R. (2018). Fixed-sized representation learning from offline handwritten signatures of different sizes, International Journal on Document Analysis and Recognition (IJDAR) 21(3): 219-232.
• [13] Hafemann, L.G., Sabourin, R. and Oliveira, L.S. (2017). Learning features for offline handwritten signature verification using deep convolutional neural networks, Pattern Recognition 70(C): 163-176.
• [14] Hameed, M.M., Ahmad, R., Kiah, L.M., Murtaza, G. and Mazhar, N. (2023). OffSig-SinGAN: A deep learning-based image augmentation model for offline signature verification, Computers, Materials & Continua 76(1): 1267-1289.
• [15] Hameed, M.M., Ahmad, R., Kiah, M.L.M. and Murtaza, G. (2021). Machine learning-based offline signature verification systems: A systematic review, Signal Processing: Image Communication 93: 116139.
• [16] Impedovo, D. and Pirlo, G. (2008). Automatic signature verification: The state of the art, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews) 38(5): 609-635.
• [17] Ioffe, S. and Szegedy, C. (2015). Batch normalization: Accelerating deep network training by reducing internal covariate shift, arXiv: 1502.03167.
• [18] Ji, X., Suehiro, D. and Uchida, S. (2023). Paired contrastive feature for highly reliable offline signature verification, Pattern Recognition 144(C): 109816.
• [19] Kalera, M.K., Srihari, S. and Xu, A. (2004). Offline signature verification and identification using distance statistics, International Journal of Pattern Recognition and Artificial Intelligence 18(07): 1339-1360.
• [20] Kaur, H.P. and Kumar, M. (2021). Signature identification and verification techniques: State-of-the-art work, Journal of Ambient Intelligence and Humanized Computing 14: 1027-1045.
• [21] Kholmatov, A. and Yanikoglu, B. (2005). Identity authentication using improved online signature verification method, Pattern Recognition Letters 26(15): 2400-2408.
• [22] Kingma, D.P. and Ba, J. (2014). Adam: A method for stochastic optimization, arXiv: 1412.6980.
• [23] Lai, S., Jin, L. and Yang, W. (2017). Online signature verification using recurrent neural network and length-normalized path signature descriptor, 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), Vol. 01, Kyoto, Japan, pp. 400-405.
• [24] Lecun, Y., Bottou, L., Bengio, Y. and Haffner, P. (1998). Gradient-based learning applied to document recognition, Proceedings of the IEEE 86(11): 2278-2324.
• [25] Li, H., Wei, P. and Hu, P. (2021). Static-dynamic interaction networks for offline signature verification, Proceedings of the AAAI Conference on Artificial Intelligence 35(3): 1893-1901.
• [26] Longjam, T., Kisku, D.R. and Gupta, P. (2023). Writer independent handwritten signature verification on multi-scripted signatures using hybrid CNN-BiLSTM: A novel approach, Expert Systems with Applications 214(C): 119111.
• [27] Maaten, L.v.d. and Hinton, G. (2008). Visualizing data using t-SNE, Journal of Machine Learning Research 9(Nov): 2579-2605.
• [28] Minaee, S., Abdolrashidi, A., Su, H., Bennamoun, M. and Zhang, D. (2023). Biometrics recognition using deep learning: A survey, Artificial Intelligence Review 56(8): 8647-8695.
• [29] Müller, R., Kornblith, S. and Hinton, G.E. (2019). When does label smoothing help?, in H.M. Wallach et al. (Eds), Advances in Neural Information Processing Systems, Red Hook, NY, USA, pp. 4694-4703.
• [30] Ortega-Garcia, J., Fierrez-Aguilar, J., Simon, D., Gonzalez, J., Faundez-Zanuy, M., Espinosa, V., Satue, A., Hernaez, I., Igarza, J.-J., Vivaracho, C., Escudero, D. and Moro, Q.-I. (2003). MCYT baseline corpus: A bimodal biometric database, IEE Proceedings-Vision, Image and Signal Processing 150(6): 395-401.
• [31] Parcham, E., Ilbeygi, M. and Amini, M. (2021). Cbcapsnet: A novel writer-independent offline signature verification model using a cnn-based architecture and capsule neural networks, Expert Systems with Applications 185(C): 115649.
• [32] Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., Antiga, L. et al. (2019). PyTorch: An imperative style, high-performance deep learning library, in H. Wallach et al. (Eds), Advances in Neural Information Processing Systems, Curran Associates Inc., Red Hook, NY, pp. 8026-8037.
• [33] Putz-Leszczynska, J. (2015). Signature verification: A comprehensive study of the hidden signature method, International Journal of Applied Mathematics and Computer Science 25(3): 659-674, DOI: 10.1515/amcs-2015-0048.
• [34] Qiao, Y., Liu, J. and Tang, X. (2007). Offline signature verification using online handwriting registration, IEEE Conference on Computer Vision and Pattern Recognition, Minneapolis, United States, pp. 1-8.
• [35] Radhika, K. and Gopika, S. (2015). Online and offline signature verification: A combined approach, Procedia Computer Science 46(C): 1593-1600.
• [36] Ren, J.-X., Xiong, Y.-J., Zhan, H. and Huang, B. (2023). 2c2s: A two-channel and two-stream transformer based framework for offline signature verification, Engineering Applications of Artificial Intelligence 118(C): 105639.
• [37] Sadak, M.S., Kahraman, N. and Uludağ, U. (2022). Dynamic and static feature fusion for increased accuracy in signature verification, Signal Processing: Image Communication 108(C): 116823.
• [38] Sekhar V., C., Gautam, A., Pulabaigari, V., S.R., S. and Sai G., R.K. (2023). TSOSVNet: Teacher-student collaborative knowledge distillation for online signature verification, IEEE/CVF International Conference on Computer Vision, ICCV 2023, Paris, France, pp. 742-751.
• [39] Tolosana, R., Vera-Rodriguez, R., Fierrez, J. and Ortega-Garcia, J. (2018). Exploring recurrent neural networks for on-line handwritten signature biometrics, IEEE Access 6: 5128-5138.
• [40] Tolosana, R., Vera-Rodríguez, R., Fiérrez, J. and Ortega-Garcia, J. (2021). Deepsign: Deep on-line signature verification, IEEE Transactions on Biometrics, Behavior, and Identity Science 3(2): 229-239.
• [41] Touvron, H., Vedaldi, A., Douze, M. and Jégou, H. (2019). Fixing the train-test resolution discrepancy, in H. Wallach et al. (Eds), Advances in Neural Information Processing Systems, Curran Associates Inc., Red Hook, NY, pp. 8252-8262.
• [42] Uppalapati, D. (2007). Integration of Offline and Online Signature Verification Systems, Master’s thesis, IIT Kanpur.
• [43] Vargas, F., Ferrer, M., Travieso, C. and Alonso, J. (2007). Off-line handwritten signature GPDS-960 corpus, 9-th International Conference on Document Analysis and Recognition (ICDAR 2007), Vol. 2, Curitiba, Brazil, pp. 764-768.
• [44] Viana, T.B., Souza, V.L., Oliveira, A.L., Cruz, R.M. and Sabourin, R. (2023). A multi-task approach for contrastive learning of handwritten signature feature representations, Expert Systems with Applications 217(C): 119589.
• [45] Vorugunti, C., Gautam, A. and Pulabaigari, V. (2023). Osvcontramer: A hybrid cnn and transformer based online signature verification, Proceedings of the IEEE International Joint Conference on Biometrics (IJCB), Ljubljana, Slovenia, pp. 1-10.
• [46] Vorugunti, C.S., Devanur S.G., Mukherjee, P. and Pulabaigari, V. (2019). Osvnet: Convolutional siamese network for writer independent online signature verification, International Conference on Document Analysis and Recognition (ICDAR), Sydney, Australia, pp. 1470-1475.
• [47] Xie, L., Wu, Z., Zhang, X. and Li, Y. (2023). Synchronous spatio-temporal signature verification via fusion triplet supervised network, Engineering Applications of Artificial Intelligence 123(B): 106378.
• [48] Xie, L., Wu, Z., Zhang, X., Li, Y. and Wang, X. (2022). Writer-independent online signature verification based on 2D representation of time series data using triplet supervised network, Measurement 197(6): 111312.
• [49] Xiong, Y.-J., Cheng, S.-Y., Ren, J.-X. and Zhang, Y.-J. (2023). Attention-based multiple siamese networks with primary representation guiding for offline signature verification, International Journal on Document Analysis and Recognition 27(2): 195-208.
• [50] Yılmaz, M.B. and Öztürk, K. (2019). Recurrent binary patterns and CNNs for offline signature verification, in A. Kohei et al. (Eds) Proceedings of the Future Technologies Conference, San Francisco, United States, pp. 417-434.
• [51] Yılmaz, M.B. and Yanıkoğlu, B. (2016). Score level fusion of classifiers in off-line signature verification, Information Fusion 32(B): 109-119.
• [52] Yu, H. and Shi, P. (2023). A novel deep ensemble framework for online signature verification using temporal and spatial representation, in D. Wang et al. (Eds), Information and Communications Security, Springer, Singapore, pp. 534-549.
• [53] Yılmaz, M.B. and Öztürk, K. (2018). Hybrid user-independent and user-dependent offline signature verification with a two-channel CNN, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, Salt Lake City, United States, pp. 526-534.
• [54] Zagoruyko, S. and Komodakis, N. (2015). Learning to compare image patches via convolutional neural networks, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, United States, pp. 4353-4361.
• [55] Zhang, X., Wang, Y., Sun, W., Cui, Q. and Wei, X. (2023). Multi-path attention inverse discrimination network for offline signature verification, Intelligent Automation & Soft Computing 36(3): 3057-3071.
• [56] Zimmer, A. and Ling, L.L. (2008). Offline signature verification system based on the online data, EURASIP Journal on Advances in Signal Processing 2008(1): 492910.
• [57] Zois, E.N., Alexandridis, A. and Economou, G. (2019). Writer independent offline signature verification based on asymmetric pixel relations and unrelated training-testing datasets, Expert Systems with Applications 125(C): 14-32.
• [58] Zois, E.N., Said, S., Tsourounis, D. and Alexandridis, A. (2023). Subscripto multiplex: A Riemannian symmetric positive definite strategy for offline signature verification, Pattern Recognition Letters 167: 67-74.
• [59] Zois, E.N., Theodorakopoulos, I., Tsourounis, D. and Economou, G. (2017). Parsimonious coding and verification of offline handwritten signatures, IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Honolulu, Hawaii, United States, pp. 636-645.

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa nr POPUL/SP/0154/2024/02 w ramach programu "Społeczna odpowiedzialność nauki II" - moduł: Popularyzacja nauki (2025).