İmza Doğrulama Alanında Transfer Öğrenme Tekniklerinin ve Makine Öğrenmesi Yöntemlerinin Performans Değerlendirilmesi

Abstract

İmza doğrulama, biyometrik güvenlik sistemlerinde önemli bir rol oynamaktadır ve geleneksel yöntemler, doğrulama doğruluğunda sınırlamalara neden olabilmektedir. Ancak, geleneksel imza doğrulama tekniklerinin sınırlı veri ve özelliklerle çalışması, doğrulama süreçlerinin doğruluğunu olumsuz etkileyebilmektedir. Bu çalışmada, transfer öğrenme ve makine öğrenmesi algoritmalarının birleşimiyle, imza doğrulama alanındaki performans artışı araştırılmıştır. BHSig260 Hindi veri setinde bulunan imzalar üzerinde gerçekleştirilen deneylerde, transfer öğrenme modelleri (ResNet50, MobileNetV2, VGG16, InceptionV3, EfficientB7, DenseNet169) tek başlarına yüksek doğruluk oranları elde etmiştir, özellikle VGG16 modeli %93.77 doğruluk ile en iyi performansı göstermiştir. Çalışmanın ilerleyen aşamalarında, transfer öğrenme modellerine K-en yakın komşu (KNN), Destek Vektör Makineleri (SVM) ve Random Forest gibi makine öğrenmesi algoritmaları eklenmiş ve doğrulama performansı daha da iyileştirilmiştir. EfficientB7 + Random Forest kombinasyonu, %95.24 doğruluk ile en yüksek başarıyı elde etmiştir. Elde edilen sonuçlar, transfer öğrenme tekniklerinin makine öğrenmesi algoritmalarıyla entegrasyonunun, imza doğrulama görevlerinde doğruluk oranlarını önemli ölçüde artırdığını ortaya koymaktadır. Bu birleşim, biyometrik güvenlik sistemlerinin güvenilirliğini ve verimliliğini önemli ölçüde iyileştiren etkili bir yöntem olarak öne çıkmaktadır. Çalışmanın bulguları, imza doğrulama sistemlerinin gelecekteki gelişimi için önemli bir referans sağlayarak, bu alandaki daha hassas ve güvenilir çözümlerin geliştirilmesine katkı sunacaktır.

Keywords

• İmza doğrulama
• Makine öğrenmesi
• KNN
• SVM
• Random Forest

Performance Evaluation of Transfer Learning Techniques and Machine Learning Methods in Signature Verification

Abstract

Signature verification plays an important role in biometric security systems and traditional methods can lead to limitations in verification accuracy. However, traditional signature verification techniques work with limited data and features, which can negatively affect the accuracy of verification processes. In this study, we investigate the performance improvement in signature verification by combining transfer learning and machine learning algorithms. In the experiments performed on signatures from the BHSig260 Hindi dataset, the transfer learning models (ResNet50, MobileNetV2, VGG16, InceptionV3, EfficientB7, DenseNet169) achieved high accuracy rates on their own, especially the VGG16 model performed the best with 93.77% accuracy. In the later stages of the study, machine learning algorithms such as K-nearest neighbor (KNN), Support Vector Machines (SVM) and Random Forest were added to the transfer learning models to further improve the validation performance. The combination of EfficientB7 + Random Forest achieved the highest performance with 95.24% accuracy. The results show that the integration of transfer learning techniques with machine learning algorithms significantly improves the accuracy of signature verification tasks. This combination stands out as an effective method that significantly improves the reliability and efficiency of biometric security systems. The findings of the study will provide an important reference for the future development of signature verification systems, contributing to the development of more accurate and reliable solutions in this field.

Keywords

• Signature verification
• Machine learning
• CNN
• transfer learning
• Biometric Security
• Hindi Signature Dataset

References

1. [1] Stauffer, M., Maergner, P., Fischer, A., & Riesen, K. (2020). A survey of state of the art methods employed in the offline signature verification process. New trends in business information systems and technology: digital innovation and digital business transformation, 17-30.
2. [2] Mohammed, Q. A. A. S., Joudah, M., & Mohammed, H. (2024, October). A survey on digital signature schemes. In AIP Conference Proceedings (Vol. 3232, No. 1). AIP Publishing.
3. [3] Saripan, H., & Hamin, Z. (2011). The application of the digital signature law in securing internet banking: Some preliminary evidence from Malaysia. Procedia Computer Science, 3, 248-253.
4. [4] Vatambeti, R., Divya, N. S., Jalla, H. R., & Gopalachari, M. V. (2022). Attack Detection Using a Lightweight Blockchain Based Elliptic Curve Digital Signature Algorithm in Cyber Systems. International Journal of Safety & Security Engineering, 12(6).
5. [5] Hameed, M. M., Ahmad, R., Kiah, M. L. M., & Murtaza, G. (2021). Machine learning-based offline signature verification systems: A systematic review. Signal Processing: Image Communication, 93, 116139.
6. [6] Impedovo, D., & 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.
7. [7] Alajrami, E., Ashqar, B. A., Abu-Nasser, B. S., Khalil, A. J., Musleh, M. M., Barhoom, A. M., & Abu-Naser, S. S. (2020). Handwritten signature verification using deep learning.
8. [8] Sam, S. M., Kamardin, K., Sjarif, N. N. A., & Mohamed, N. (2019). Offline signature verification using deep learning convolutional neural network (CNN) architectures GoogLeNet inception-v1 and inception-v3. Procedia Computer Science, 161, 475-483.

9. [9] Navid, S. M. A., Priya, S. H., Khandakar, N. H., Ferdous, Z., & Haque, A. B. (2019, November). Signature verification using convolutional neural network. In 2019 IEEE International Conference on Robotics, Automation, Artificial-intelligence and Internet-of-Things (RAAICON) (pp. 35-39). IEEE.
10. [10] Parcham, E., Ilbeygi, M., & 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, 115649.
11. [11] Alsuhimat, F. M., & Mohamad, F. S. (2023). A Hybrid Method of Feature Extraction for Signatures Verification Using CNN and HOG a Multi-Classification Approach. IEEE Access, 11, 21873-21882.
12. [12] Ghosh, R. (2021). A Recurrent Neural Network based deep learning model for offline signature verification and recognition system. Expert Systems with Applications, 168, 114249.
13. [13] Sharma, N., Gupta, S., Mehta, P., Cheng, X., Shankar, A., Singh, P., & Nayak, S. R. (2022). Offline signature verification using deep neural network with application to computer vision. Journal of Electronic Imaging, 31(4), 041210-041210.
14. [14] Hanmandlu, M., Sronothara, A. B., & Vasikarla, S. (2018, November). Deep learning based offline signature verification. In 2018 9th IEEE Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON) (pp. 732-737). IEEE.
15. [15] Pinzón-Arenas, J. O., Jiménez-Moreno, R., & Pachón-Suescún, C. G. (2019). Offline signature verification using DAG-CNN. International Journal of Electrical & Computer Engineering (2088-8708), 9(4).
16. [16] Naz, S., Bibi, K., & Ahmad, R. (2022). DeepSignature: fine-tuned transfer learning based signature verification system. Multimedia Tools and Applications, 81(26), 38113-38122.
17. [17] Yapıcı, M. M., Tekerek, A., & Topaloğlu, N. (2021). Deep learning-based data augmentation method and signature verification system for offline handwritten signature. Pattern Analysis and Applications, 24(1), 165-179.
18. [18] Hazra, A., Maity, S., Pal, B., & Bandyopadhyay, A. (2024). Adversarial attacks in signature verification: a deep learning approach. Computer Science and Information Technologies, 5(3), 215-226.
19. [19] Attri, V. K., Jaiswal, T., Singh, B., Bansal, P., Sarangal, H., Kaur, S., & Kaur, H. (2024, January). Signature Verification Using Deep Learning: An Empirical Study. In International Conference on Advances in Distributed Computing and Machine Learning (pp. 175-187). Singapore: Springer Nature Singapore.
20. [20] Singh, A., & Viriri, S. (2020, March). Online signature verification using deep descriptors. In 2020 Conference on information communications technology and society (ICTAS) (pp. 1-6). IEEE.
21. [21] Suganthe, R. C., Geetha, M., Sreekanth, G. R., Manjunath, R., Krishna, S. M., & Balaji, P. M. (2022, January). Performance Evaluation of Convolutional Neural Network Based Models On Signature Verification System. In 2022 International Conference on Computer Communication and Informatics (ICCCI) (pp. 1-6). IEEE.
22. [22] Alvarez, G., Sheffer, B., & Bryant, M. (2016). Offline signature verification with convolutional neural networks. In Technical report, Stanford University.
23. [23] Hameed, M. M., Ahmad, R., Kiah, M. L. M., & Murtaza, G. (2021). Machine learning-based offline signature verification systems: A systematic review. Signal Processing: Image Communication, 93, 116139.
24. [24] Pan, S. J., & Yang, Q. (2009). A survey on transfer learning. IEEE Transactions on Knowledge and Data Engineering, 22(10), 1345–1359. https://doi.org/10.1109/TKDE.2009.191
25. [25] Bengio, Y. (2009). Learning Deep Architectures for AI.
26. [26] Pan, S. J., & Yang, Q. (2009). A survey on transfer learning. IEEE Transactions on knowledge and data engineering, 22(10), 1345-1359.
27. [27] Yosinski, J., Clune, J., Bengio, Y., & Lipson, H. (2014). How transferable are features in deep neural networks?. Advances in neural information processing systems, 27.
28. [28] Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., & Chen, L. C. (2018). Mobilenetv2: Inverted residuals and linear bottlenecks. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 4510-4520).
29. [29] He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 770-778).
30. [30] Huang, G., Liu, Z., Van Der Maaten, L., & Weinberger, K. Q. (2017). Densely connected convolutional networks. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 4700-4708).
31. [31] Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., & Wojna, Z. (2016). Rethinking the inception architecture for computer vision. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 2818-2826).
32. [32] Tan, M., & Le, Q. (2019, May). Efficientnet: Rethinking model scaling for convolutional neural networks. In International conference on machine learning (pp. 6105-6114). PMLR.
33. [33] Cover, T., & Hart, P. (1967). Nearest neighbor pattern classification. IEEE transactions on information theory, 13(1), 21-27.
34. [34] Cortes, C. (1995). Support-Vector Networks. Machine Learning.
35. [35] Breiman, L. (2001). Random forests. Machine learning, 45, 5-32.
36. [36] Yosinski, J., Clune, J., Bengio, Y., & Lipson, H. (2014). How transferable are features in deep neural networks?. Advances in neural information processing systems, 27.
37. [37] Oquab, M., Bottou, L., Laptev, I., & Sivic, J. (2014). Learning and transferring mid-level image representations using convolutional neural networks. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 1717-1724).