College of Computer Science and Mathematics

Discussion of a High diploma thesis in the College of Computer Science and Mathematics – Department of Software entitled:

“Signature Identification System Based on Verification Process in Software Engineering”

In continuation of the scientific research movement and with the follow-up and presence of the Dean of the College of Computer Science and Mathematics

Respected Professor Dr. Duha Bashir Abdullah

It was discussed in the discussion hall of the College of Computer  Science and Mathematics at the University of Mosul on Sunday 18/2/2024

high diploma thesis by

Ahmad Abdulkareem Bilal

supervised by Asist.Prof. Dr Naktal Moaid Edan

Biometric technologies have revolutionized personal identification and security systems by leveraging unique physiological or behavioral traits. Thus, these handwritten signatures are widely used for authentication. Signature recognition is one kind of behavioral biometric that recognizes a person by their handwriting. There are two distinct modes of operation: static and dynamic. Users write their signatures in the static mode on paper, which is subsequently scanned digitally with an optical scanner or a camera to produce a bitmap representation of the signature. The signature’s shape is then examined by the biometric system to confirm its identity. Also referred to as “off-line” is this group. On the other hand, dynamic signatures—also referred to as “online” signatures—are captured in real time by a digitizing tablet where users write their signatures. Accordingly, signature recognition can be used for various purposes, including document authentication, access control, and financial transactions. It is commonly used in banks and other financial institutions to verify the identity of customers signing checks, authorizing withdrawals, or completing other transactions. The main aim in this research is to design and implement a novel tool for identifying a signature based on Software Engineering (SE) process, such as Verification and Validation (V&V) process, without using Machin Learning (ML) or external software. Therefore, a hybrid algorithm has been created and implemented using Python language in PyCharm Community Edition as an environment and based on three algorithms, such as Find Contour, the Oriented FAST and Rotated BRIEF (ORB) key point matching technique with the Absolute Difference Algorithm for signature recognition. Moreover, it has generated and applied a dataset of 110 signatures manually; so the results validated that it has obtained a performance of the designed tool that is 91% accuracy rate of the comparison among signatures. This tool underperforms previous researchs by offering practical applicability and closer to the real world. Not only that but also, this tool offers a user-friendly graphical interface for signature similarity proven.

The discussion committee consists of:

Prof. Dr. Laheeb Mohammad Ibrahim – Chairman

Assis. Prof.  Tawfeeq Moqdad Tawfeeq– Member

Assist. Prof. Dr. Naktal Moaid Edan – Member and supervisor