Oladele, T .O. and Adewole, K. S. and Oyelami, A. O. and Abiodun, Theresa Nkechi (2014) Forged Signature Detection Using Artificial Neural Network. African Journal of Computing & ICT, 7 (3). 11-20-. ISSN 2006-1781
PDF
Download (748kB) |
Abstract
Crimes and corruptions are practices that gradually cripple the economy of a nation most especially in Nigeria. Nigerian government has strived hard to reduce these acts perpetrated by the citizens. This is evident in the struggles of Economic and Financial Crime Commission (EFCC) and Independence Corrupt Practices and other Related Offences Commission (ICPC) to reduce frauds in both public and private sectors due to signature forgery which attempts to commit financial crimes and other related offences. Forged signature is an illegal copy of signature that looks like a genuine signature usually used for financial fraud. Identity verification (authentication) in computer systems has been traditionally based on something that one has such as key, magnetic or chip card or that one knows such as PIN or password. Things like keys or cards, however, tend to get stolen or lost and passwords are often forgotten or disclosed. In this paper, a neural network algorithm was employed to develop a system that can verify and detect forged signatures. The effect of the signature verification and detection is discussed and its impact on the economy is highlighted. Result of the proposed Java application shows its capability in detecting forged signatures. The system has the capability to learn from previous data and to assist EFCC and ICPC in detecting and investigating fraudulent activities
Item Type: | Article |
---|---|
Uncontrolled Keywords: | Neural Network, Algorithm, Biometrics, Signature & Forgery |
Subjects: | Q Science > QA Mathematics > QA75 Electronic computers. Computer science |
Divisions: | Faculty of Engineering, Science and Mathematics > School of Electronics and Computer Science |
Depositing User: | Patricia Nwokealisi |
Date Deposited: | 21 Aug 2024 10:20 |
Last Modified: | 21 Aug 2024 10:20 |
URI: | http://eprints.covenantuniversity.edu.ng/id/eprint/18390 |
Actions (login required)
View Item |