Authors : M. Varsha; Prakash O. S.; Dr. Girish Kumar D.

Volume/Issue : Volume 11 - 2026, Issue 4 - April

---

Google Scholar : https://tinyurl.com/2nm5bj82

Scribd : https://tinyurl.com/2v5rvp9e

DOI : https://doi.org/10.38124/ijisrt/26apr2506

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

---

Abstract : Handwritten signatures are commonly used for identify authentication across banking, legal, and academic sectors. However, manual verification is slow and unreliable, especially when forged signatures closely resemble genuine ones. To overcome this limitation, this work proposes an intelligent offline signature verification system. The system analyzes scanned or photographed signature images to identify whether they are genuine or forged. Image preprocessing steps such as resizing, noise removal, and normalization are applied to enhance image quality. The CNN model automatically learns key features like stroke patterns and writing structure, eliminating manual feature extraction. The proposed approach improves accuracy, reduces human effort, and provides a reliable solution for secure real-world signature verification.

Keywords : Signature Forgery, Forgery Classification, Document Authentication, Machine Learning, Feature Extraction, Security and Authentication.

References :

1. A. Kumar, S. Gupta, and R. Sharma, “Deep learning– based offline handwritten signature verification using optimized CNN architectures,” IEEE Access, vol. 13, pp. 11245–11258, 2025.
2. M. Elhoseny, K. Shankar, and A. Abdel-Basset, “Robust offline signature verification framework usingconvolutional neural networks,” Pattern Recognition Letters, vol. 176, pp. 45–53, 2025.
3. S. Reddyand P. R. Kumar, “Scalable CNN-based offline signature verification for financial and institutional authentication,” Journal of Information Security and Applications, vol. 82, pp. 103768, 2025.
4. R. Patel and V. Shah, “Offline handwritten signature verification using deep convolutional features,” Expert Systems with Applications, vol. 238, pp. 121893, 2024.
5. H. Bansal, A. Verma, and N. Jain, “Automated signature forgery detection using deep neural networks,” Neural Computing andApplications,vol.36,no.4,pp.1821–1834, 2024.
6. P. Singh and S. Kumar, “A comparative study of CNN architectures for offline signature verification,”International Journal of Pattern Recognition and Artificial Intelligence, vol. 38, no. 6, 2024.
7. S. Hafemann, R. Sabourin, and L. Oliveira, “Offline handwritten signature verification using deep learning: Recent advances and trends,” IEEE Transactions on Information Forensics and Security, vol. 19, pp.2451–2464, 2024.
8. A. Chugh, R. Jain, and M. Gupta, “Offline signature verification using hybrid CNN and feature learning techniques, ”Multimedia Tools and Applications, vol. 83,pp. 39125–39142, 2023.
9. M. Yılmaz and B. Ergen, “CNN-based offline signature authentication with enhanced preprocessing,” Signal, Image and Video Processing, vol. 17, no. 3, pp. 1081–1089, 2023.
10. K. S. Reddyand D. R. Reddy, “Deep learning approach for skilled forgery detection in offline signatures,” Journalof King Saud University – Computer and Information Sciences, vol. 35, no. 8, pp. 101692, 2023.
11. T. Roy, S. Banerjee, and A. Ghosh, “Automatic offline signature verification using convolutional neural networks,” Procedia Computer Science, vol. 218,pp.1121–1128,2023.
12. A. Sharma and P. Kaur, “Offline handwritten signature verification using deep convolutional neural networks,” International Journal of Computer Vision and Image Processing, vol. 12, no. 2, pp. 1–16, 2022.
13. F. Alonso-Fernandez and J. Bigun, “Off-line signature verification: Recent trends and comparative analysis,” IEEE Access, vol.10, pp.45789–45802, 2022.