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{193967,
        author = {Nithya Priya Gurram and Bapini Pranavi and D. Navyasri},
        title = {Detection of Handwritten Signature Forgery Using Machine Learning and Hybrid Feature Extraction},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {10},
        pages = {3117-3123},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=193967},
        abstract = {Handwritten signature verification still remains a problem in biometric authentication, because static images don’t have dynamic information like writing speed, stroke order. Skilled forgeries often resemble genuine signatures which makes detection difficult. In this project we proposed an automated signature forgery detection system, which uses a dynamic Best Classifier section pipeline. This approach extracts around 8140 features from those signature images by combining the Histogram of Gradient with statistical features. Those extracted features are used for training all 9 different ML algorithms to identify the best algorithm. Best Classifier actually outperforms SVM, Random Forest, KNN. This proposed approach reaches an accuracy of 96% with a precision of 97.2% recall of 95.8% F1 score of 96.5% which indicates its effectiveness of signature forgery detection.},
        keywords = {Automated Biometric Authentication, Dynamic Best Classifier Pipeline, Financial Fraud Prevention, Histogram of Oriented Gradients (HOG), Hybrid Feature Extraction, Machine Learning, Offline Handwritten Signatures, Signature Forgery Detection, Static Document Analysis, Support Vector Machine Comparison.},
        month = {March},
        }