Copyright © 2025 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{185872,
        author = {GAJULA PARIMALA and CH. SATYANANDA REDDY},
        title = {HANDWRITTEN SIGNATURE VERIFICATION USING DEEP LEARNING},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {5},
        pages = {2901-2904},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=185872},
        abstract = {Handwritten signatures remain one of the most widely used biometric modalities for personal authentication and identity verification in financial, legal, and security systems. Traditional machine learning approaches to signature verification rely on handcrafted features and classical classifiers, often failing to generalize across intra-class variations and skilled forgeries. This paper presents a deep learning–based approach leveraging Convolutional Neural Networks (CNNs) combined with a Triplet Loss embedding model (EfficientTriplet) to generate discriminative feature representations of handwritten signatures. The system computes similarity scores between signature embeddings to classify them as genuine or forged. Extensive experiments conducted on benchmark datasets (CEDAR, GPDS, and Kaggle Signature Verification) demonstrate the robustness of the proposed model, achieving a verification accuracy of above 95%. The implementation is extended with a Flask-based web application to provide a user-friendly interface for real-time signature verification. This research highlights the potential of deep metric learning in combating skilled forgeries and enabling secure, scalable identity verification systems.},
        keywords = {Signature Verification, Deep Learning, Triplet Loss, Embedding Networks, Cosine Similarity, Flask API, Biometric Authentication.},
        month = {October},
        }