Leveraging Machine Learning Techniques for Enhancing Signature Verification to Unveiling the Forgery

Abstract

These days, computer vision and machine learning researchers are actively studying handwritten signature verification. It makes sense to define signature verification as a machine-learning task. This is accomplished by figuring out if the signature is real or fake. It is therefore regarded as a two-class classification problem. Given the prevalence of handwritten signatures in legal documents and financial transactions, researchers must carefully consider which machine-learning technique to apply in order to authenticate handwritten signatures and prevent forgeries that could result in significant losses for their clients. Thus far, the application of machine learning algorithms has produced excellent results in terms of equal computation error rates.  The research aims to develop a model of classification capable of effectively categorizing forged verified signatures using input data. The primary objective is to explore the creation of a robust signature verification classification model using machine learning and algorithms. The research design involves a step-by-step approach design includes the gathering of data, Preprocessing, classification algorithms, and evaluation of models. The process of verifying the authenticity of a signature by use of machine learning techniques is called signature verification. The present project concentrates on off-line signature verification, however signatures might be of either online or offline form. This project intends to create a methodology that uses writer-independent characteristics to differentiate between authentic and faked signatures. In order to collect signatures from people, execute signature verification, and display the outcomes, we want to develop a whole end-to-end hardware/software system. To achieve this, a number of Machine Learning approaches for off-line signature verification were created and evaluated on benchmark datasets. Our proposed technique outperforms offline signature verification approaches such as support vector machine (SVM), neural network (NN), and logistic regression in terms of accuracy.

REFERENCES

[1] H. A. Salman and H. Abdul wahab, “Anti-screenshot keyboard for web-based application using cloaking,” in Proc. Int. Conf. Adv. Intell. Syst. Inform., 2020, pp. 473–478, doi: 10.1007/978-3-030-21005-2_45.

[2] F. M. Alsuhimat and F. S. Mohamad, “Offline signature verification using long short-term memory and histogram orientation gradient,” Bull. Electr. Eng. Informatics, vol. 12, no. 1, pp. 10–19, Feb. 2023, doi: 10.11591/eei.v12i1.4024.

[3] A. Hamadene and Y. Chibani, “One-class writer-independent offline signature verification using feature dissimilarity thresholding,” IEEE Trans. Inf. Forensics Security, vol. 11, no. 6, pp. 1226–1238, Jun. 2016, doi: 10.1109/TIFS.2016.2521611.

[4] Z. Hashim, H. M. Ahmed, and A. H. Alkhayyat, “A comparative study among handwritten signature verification methods using machine learning techniques,” Sci. Program., vol. 2022, p. 8170424, Jan. 2022, doi: 10.1155/2022/8170424.

[5] Sam et al., “Offline signature verification using deep learning convolutional neural network (CNN) architectures GoogLeNet Inception-v1 and Inception-v3,” Procedia Comput. Sci., vol. 161, pp. 475–483, 2019, doi: 10.1016/j.procs.2019.11.147.

[6] M. Kurowski, A. Sroczyński, G. Bogdanis, and A. Czyżewski, “An automated method for biometric handwritten signature authentication employing neural networks,” Electronics, vol. 10, no. 4, p. 456, Feb. 2021, doi: 10.3390/electronics10040456.

[7] I. Alim, N. Imtiaz, A. Al Prince, and M. A. Hasan, “AI and blockchain integration: Driving strategic business advancements in the intelligent era,” J. Eng. Comput. Intell. Rev., vol. 3, no. 2, pp. 38–50, 2025.

[8] M. Z. Afshar and M. H. Shah, “A narrative review for revisiting BCG matrix application in performance evaluation of public sector entities,” J. Res. Rev., vol. 2, no. 02, pp. 325–337, 2025.

[9] F. Leclerc and R. Plamondon, “Automatic signature verification: The state of the art - 1989-1993,” Int. J. Pattern Recognit. Artif. Intell., vol. 8, no. 3, pp. 643–660, Sep. 1994, doi: 10.1142/S0218001494000346.

[10] F. S. Mohamad, F. M. Alsuhimat, M. A. Mohamed, M. Mohamad, and A. A. Jamal, “Detection and feature extraction for images signatures,” Int. J. Eng. Technol., vol. 7, no. 3, pp. 44–48, 2018.

[11] R. Plamondon and G. Lorette, “Automatic signature verification and writer identification — the state of the art,” Pattern Recognit., vol. 22, no. 2, pp. 107–131, 1989, doi: 10.1016/0031-3203(89)90059-9.

[12] D. Ali and T. Ahmed, “Computational analysis of geothermal-enhanced heavy oil production,” J. Eng. Comput. Intell. Rev., vol. 2, no. 2, pp. 10–20, 2024.

[13] M. Z. Afshar and M. H. Shah, “Leveraging Porter's Diamond Model: Public Sector Insights,” Crit. Rev. Soc. Sci. Stud., vol. 3, no. 2, pp. 2255–2271, 2025.

[14] K. S. Radhika and S. Gopika, “Online and offline signature verification: A combined approach,” Procedia Comput. Sci., vol. 46, pp. 1593–1600, 2015, doi: 10.1016/j.procs.2015.02.089.

[15] R. Amin and A. A. Kazmi, “Smart grids: A comprehensive review of technologies, challenges, and future directions,” J. Eng. Comput. Intell. Rev., vol. 2, no. 2, pp. 45–70, 2024.

[16] T. A. Shiva, J. G. Brown, A. A. McField, R. E. Osborne, and C. D. Oberle, “Cultural associations with prosocial behaviors and attitudes among Asian Americans,” Asian Am. J. Psychol., 2025, early access.

[17] M. Sharif, M. A. Khan, M. Faisal, M. Yasmin, and S. L. Fernandes, “A framework for offline signature verification system: Best features selection approach,” Pattern Recognit. Lett., vol. 139, pp. 50–59, Nov. 2020, doi: 10.1016/j.patrec.2018.01.021.

[18] D. Suryani, E. Irwansyah, and R. Chindra, “Offline signature recognition and verification system using efficient fuzzy kohonen clustering network (EFKCN) algorithm,” Procedia Comput. Sci., vol. 116, pp. 621–628, 2017, doi: 10.1016/j.procs.2017.10.025.

[19] M. A. Saputra and I. Nurhaida, “Signature originality verification using a deep learning approach,” Electron. J. Educ. Soc. Econ. Technol., vol. 5, no. 1, pp. 19–29, 2024.

[20] N. Patel, P. J. Patel, and A. Changa, “Exploring the effectiveness of machine learning algorithms in image forgery detection,” Int. J. Sci. Res. Comput. Sci. Eng. Inf. Technol., vol. 10, no. 1, pp. 45–54, 2024.

[21] M. Asif, "Contingent effect of conflict management towards psychological capital and employees’ engagement in financial sector of Islamabad," Ph.D. dissertation, Preston Univ., Kohat, Islamabad Campus, Pakistan, 2021.

[22] M. Asif and A. Shaheen, "Creating a high-performance workplace by the determination of importance of job satisfaction, employee engagement, and leadership," Journal of Business Insight and Innovation, vol. 1, no. 2, pp. 9-15, 2022.

[23] M. Asif, "Mediating role of trust between emotional intelligence and project team performance in telecommunication sector," Journal of Business Insight and Innovation, vol. 1, no. 2, pp. 9-15, 2022. (Note: Assumed journal based on context; please verify if this is correct.)

[24] Aurangzeb, M. Asif, and M. K. Amin, "Resources management and SME's performance," Humanities & Social Sciences Reviews, 2021, doi: 10.18510/hssr.2021.

[25] M. A. Pasha, M. Ramzan, and M. Asif, "Impact of economic value added dynamics on stock prices fact or fallacy: New evidence from nested panel analysis," Global Social Sciences Review, vol. 4, no. 3, pp. 135-147, 2019.

[26] S. H. Alizai, M. Asif, and Z. K. Rind, "Relevance of motivational theories and firm health," International Journal of Management (IJM), vol. 12, no. 3, pp. 1130-1137, 2021.

[27] Aurangzeb, T. Mushtaque, M. N. Tunio, Zia-ur-Rehman, and M. Asif, "Influence of administrative expertise of human resource practitioners on the job performance: Mediating role of achievement motivation," International Journal of Management (IJM), vol. 12, no. 4, pp. 408-421, 2021.

[28] M. Asif, M. A. Pasha, and A. Shahid, "Energy scarcity and economic stagnation in Pakistan," Bahria University Journal of Management & Technology, vol. 8, no. 1, pp. 141-157, 2025.

[29] A. Mumtaz, N. Munir, R. Mumtaz, M. Farooq, and M. Asif, "Impact of psychological & economic factors on investment decision-making in Pakistan Stock Exchange," Journal of Positive School Psychology, vol. 7, no. 4, pp. 130-135, 2023.

[30] M. Asif, H. Shah, and H. A. H. Asim, "Cybersecurity and audit resilience in digital finance: Global insights and the Pakistani context," Journal of Asian Development Studies, vol. 14, no. 3, pp. 560-573, 2025.

[31] M. Asif, "The complexities of bioterrorism: Challenges and considerations," International Journal of Contemporary Issues in Social Sciences, vol. 3, no. 3, pp. 2175–2184, 2024.

[32] Dr. Aurangzeb and M. Asif, "Role of leadership in digital transformation: A case of Pakistani SMEs," in 2021 Fourth International Conference on Emerging Trends in Engineering, Management and Sciences (ICETEMS), Oct. 13-14, 2021, vol. 4, no. 1, pp. 219-229.

[33] H. A. Usama, M. Riaz, A. Khan, N. Begum, M. Asif, and M. Hamza, "Prohibition of alcohol in Quran and Bible (A research and analytical review)," PalArch's Journal of Archaeology of Egypt/Egyptology, vol. 19, no. 4, pp. 1202-1211, 2022.