Signature Fraud Detection using Deep Learning

IEEE BASE PAPER ABSTRACT:

Image analytics solutions are very crucial for not only security, but also for authentication purposes. One such intriguing new Deep Learning application is automatic signature verification. Signed papers are the foundation of all transactions and governance in banks and government agencies, to mention a few examples. Verifying signatures on these documents is an important aspect of the back-office operations. Manual signature verification is not only time intensive, but also prone to mistakes and possible fraud. These flaws may be removed using AI-based automated signature analysis, resulting in considerable efficiency benefits. Based on the Siamese Neural Network, this research proposes an offline solution for signature identification and verification. To construct a feature vector, a collection of global features is utilised.

PROJECT OUTPUT VIDEO:

ALGORITHM / MODEL USED:

Siamese Neural Networks.

OUR PROPOSED PROJECT ABSTRACT:

The growing digital landscape has increased the need for robust and efficient fraud detection systems. This project presents a unique approach to detecting signature fraud using deep learning techniques, specifically employing Siamese Neural Networks, implemented in Python.

With a dataset comprising 2149 signature images, encompassing both genuine and fraudulent samples from Dutch users, our model demonstrates remarkable accuracy. The Siamese Neural Network architecture excels in signature verification tasks by learning to distinguish between genuine and fraudulent signatures through contrastive learning.

The key achievement of this project is the exceptional accuracy levels attained during the training and validation phases. The model’s training accuracy stands at an impressive 98.00%, while the validation accuracy reaches an astonishing 99.00%. These high accuracy rates are a testament to the effectiveness of Siamese Neural Networks in signature fraud detection.

In a world where the security of digital signatures is paramount, this project showcases the power of deep learning and Siamese Neural Networks in safeguarding against fraudulent activities. The model’s success in accurately distinguishing between authentic and forged signatures offers promising potential for enhancing security measures in various domains, including finance, legal, and document management.

SYSTEM REQUIREMENTS:

HARDWARE REQUIREMENTS:

System : Pentium i3 Processor.
Hard Disk : 500 GB.
Monitor : 15’’ LED.
Input Devices : Keyboard, Mouse.
Ram : 8 GB.

SOFTWARE REQUIREMENTS:

Operating system : Windows 10 Pro.
Coding Language : Python 3.10.9.
Web Framework : Flask.
Frontend : HTML, CSS, JavaScript.

REFERENCE:

Hindumathi; Jennifer Chalichemala; Endla Ameya; Vatadi Kavya Sri; Bhople Vaibhavi, “Offline Handwritten Signature Verification using Image Processing Techniques”, 2023 IEEE 8th International Conference for Convergence in Technology (I2CT), IEEE Conference, 2023.

Python IEEE Projects

Signature Fraud Detection using Deep Learning