Advanced International Journal of Multidisciplinary Research

E-ISSN: 2584-0487 •   Impact Factor: 9.11

An Open Access Peer Reviewed Multidisciplinary Bi-monthly Scholarly International Journal

Call for Paper Volume 4 Issue 2 March-April 2026 Submit your research before last 3 days of April to publish your research paper in the issue of March-April.
Submit Research Paper Join as a Reviewer

Plagiarism is checked by the leading plagiarism checker TurnItIn

Call for Paper

Volume 4 Issue 2
March-April 2026

Submit your research paper

Indexing Partners
Academia Advanced Sciences Index Bielefeld Academic Search Engine CiteSeer DRJI Google Scholar Independent Search Engine & Directory Network ISI (International Scientific Indexing) Issuu Mendeley Research Networks
RefSeek ResearcherId - Thomson Reuters ResearchGate Scribd Semantic Scholar UTeM - Universiti Teknikal Malaysia Melaka Wiki for Call for Papers WorldCat Zenodo

Signature Fraud Detection using Deep Learning

Author(s) G. Swetha, C. Umadevi, M. Govardhan, V. Tharun, M. C Bhanu Prasad
Country India
Abstract Signature verification is commonly used for the signature is real or fake. Signatures are used in banks, offices, and legal documents. Fraudulent signatures can cause serious financial loss. Manual signature verification is not always reliable. Human errors may occur during verification. Therefore, an automatic signature fraud detection system is needed. This project focuses on signature fraud detection using deep learning methods. The system works with offline handwritten signature images. Signature samples are collected from different individuals. These samples are converted into digital image format. Image preprocessing is performed to remove noise. Image resizing and normalization are also applied. Convolutional Neural Network (CNN) is used for feature extraction. CNN helps in identifying important signature patterns. It learns features such as shape, curves, and strokes. CNN improves accuracy in image classification tasks. It reduces the need for manual feature selection. Siamese Neural Network is used for signature comparison. It compares two signature images at a time. The network checks similarity between input signatures. It determines whether the signatures belong to the same person. Siamese network is effective for verification problems. The system compares test signatures with stored reference signatures. Based on similarity score, the signature is verified. The output shows whether the signature is genuine or forged. The model is trained using labeled signature data. Testing is done using unknown signature samples. The performance is measured using accuracy and error rate. The system provides fast and reliable results. It reduces dependency on manual verification. This method improves security in authentication systems. It is suitable for banking and document verification applications.
Keywords Signature Fraud Detection, Deep Learning, Siamese Neural Network, Biometric Authentication, Kaggle Dataset, Image Verification.
Discipline Engineering
Published In Volume 4, Issue 2, March-April 2026
Published On 2026-04-04
View / Download Full-text Research PDF File

Share this



E-ISSN 2584-0487
Downloads
Cover Page Vol 2 Isu 5 Cover Page Vol 2 Isu 4 Cover Page Vol 2 Isu 3 Research Paper Format

All research papers published on this website are licensed under Creative Commons Attribution-ShareAlike 4.0 International License, and all rights belong to their respective authors/researchers.

CC-BY-SA Open Access

About AIJMR
Fees & Payment
Current Issue
Publication Archive 		Submit Research Paper
Track Submission Status
Publication Guidelines
Publication Ethics
Peer Review & Plagiarism 		Join as a Reviewer
Editors & Reviewers
Reviewer Referral Program
Get Reviewer Membership Certi. 		Website/Journal Policies
Usage Policy
Content Policies
Privacy Policy
Contact Us +91-9687-828-838 editor@aijmr.com