Copyright © 2026 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{190680,
        author = {Dr. Annapurna H},
        title = {A Multi-Scale Zernike Feature-Based Approach for Writer-Specific Offline Signature Verification},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {8},
        pages = {1189-1196},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=190680},
        abstract = {This work presents a writer-dependent offline signature verification framework that combines multi-scale structural feature representation with discriminative classification. Initially, signature images undergo preprocessing to enhance structural consistency and reduce noise. Multi-scale patch-based Zernike moment features are then extracted to effectively capture both local and global shape characteristics of handwritten signatures. To reduce feature redundancy and improve computational efficiency, principal component analysis is applied for dimensionality reduction. For the verification stage, a writer-specific Support Vector Machine (SVM) classifier with a radial basis function kernel is employed. The proposed system is evaluated on the standard MCYT offline signature dataset using multiple training–testing split configurations to analyze robustness under varying levels of available training data. Experimental results demonstrate that increasing the number of training samples significantly improves verification performance, achieving an accuracy of 92.67% under the 75% training scenario. The obtained results confirm that the proposed framework effectively captures discriminative signature patterns and provides reliable writer-dependent verification performance, making it suitable for practical biometric authentication applications.},
        keywords = {Biometric authentication, Feature extraction, Multi-scale patch-based, Support vector machine, Writer-dependent verification, Zernike moments},
        month = {January},
        }