NORMA eResearch @NCI Library

Handwritten Signature Verification using Deep Learning Technique in Conjunction with Image Processing

Bajpai, Manish (2022) Handwritten Signature Verification using Deep Learning Technique in Conjunction with Image Processing. Masters thesis, Dublin, National College of Ireland.

[thumbnail of Master of Science]
PDF (Master of Science)
Download (1MB) | Preview
[thumbnail of Configuration manual]
PDF (Configuration manual)
Download (1MB) | Preview


Handwritten signatures have been used in financial and legal documents for a long time. It is crucial in the financial sector to distinguish between authentic handwritten signatures and forgeries. As the naked eye cannot always distinguish between real and forged signatures, the majority of handwritten signatures are accepted in banks by human intervention, which can lead to human errors or fraud. A deep neural network is used to recognize genuine handwritten signatures. In this study the VGGNet neural network is employed to recognize handwritten signatures. The case study’s evaluation metrics include accuracy, precision, and recall, which were compared to the other state of the arts in the field of handwritten signatures. The findings of this case study are designed to aid the banking industry in avoiding financial sector forgeries. The VGGNet model outperforms other state of the art models in the domain of handwritten signature datasets.

Item Type: Thesis (Masters)
Uncontrolled Keywords: Deep Neural Network; VGGNet; Image Processing; CNN
Subjects: Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science
H Social Sciences > HG Finance > Banking
Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions: School of Computing > Master of Science in Data Analytics
Depositing User: Tamara Malone
Date Deposited: 18 Jan 2023 15:27
Last Modified: 06 Mar 2023 17:05

Actions (login required)

View Item View Item