Abstract :

Handwritten Signature Verification Remains One Of The Most Widely Used Methods For Personal Authentication In Financial, Legal, And Administrative Processes. However, Manual Examination Is Time-consuming, Error-prone, And Vulnerable To Skilled Forgery Attempts. This Study Presents An Automated Detection System For Forged Handwritten Signatures Using Advanced Image Processing And Machine Learning Techniques. The Proposed Method Preprocesses Signature Samples Through Noise Removal, Normalization, And Feature Extraction Based On Shape, Stroke Dynamics, Texture, And Contour Characteristics. A Deep Learning Classifier Is Then Trained To Distinguish Between Genuine And Forged Signatures With High Accuracy. Experimental Results Demonstrate Significant Improvements In Detection Performance Compared To Traditional Manual And Rule-based Approaches, Reducing False Acceptance And Rejection Rates. The System Offers A Fast, Reliable, And Scalable Solution For Realworld Applications Such As Banking Security, Digital Document Validation, And Identity Verification. This Work Contributes Toward Enhancing Authentication Reliability And Minimizing Fraud Risks In Signature-based Systems. Keywords: Handwritten Signature Verification, Forgery Detection, Image Processing, Deep Learning, Feature Extraction, Texture Analysis, Stroke Dynamics, Authentication Systems, Biometric Security, Pattern Recognition.

Published:

11-12-2025

Issue:

Vol. 25 No. 12 (2025)

Page Nos:

137-143

Section:

Articles

License:

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

How to Cite