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{185767,
        author = {Md Dilwar Alam and Mohammad Hozaifa and Abdul Aakhir},
        title = {Deep Learning Model for Reliable Handwritten Signature Authentication},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {5},
        pages = {2706-2716},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=185767},
        abstract = {Handwritten signature verification is a biometric authentication method used in financial transactions, legal documents and security sensitive applications. However, achieving high reliability especially in offline systems is challenging due to intra-class variations and skilled forgeries. This paper evaluates the effectiveness of deep learning models for offline handwritten signature verification by testing 5 individual models: custom Convolutional Neural Network (CNN), DenseNet121, VGG16, VGG19 and ResNet50. To improve model performance advanced preprocessing techniques such as binarization, grayscale conversion, normalization, edge detection and data augmentation are applied to extract robust features. The results show that deep learning models can significantly improve the accuracy and reliability of signature verification systems. Also the paper highlights the challenges such as dataset limitations, intra-writer variations and generalization issues and suggests directions for future work to further improve the performance of such systems.},
        keywords = {offline Handwritten Signature, Deep learning, Image Processing, Data Augmentation, Convolutional Neural Network (CNN), Writer Independent.},
        month = {October},
        }