Abstract: Nowadays, people use ATMs widely. Withdrawals from ATMs are increasing day by day. The current traditional ATM is vulnerable to crime due to the rapid development of technology. With a total of 270,000 reports of bank card fraud, it was the most reported form of identity theft in 2021. This project proposes an automated teller security model that uses electronic facial recognition using a deep convolutional neural network. Face verification Click bait link is generated and sent to the bank account holder to verify the identity of the unauthorized user through some special AI agent for remote authentication. However, it is clear that human biometric characteristics cannot be imitated.. Experimental results on real-time datasets show superior performance of the proposed approach compared to state-of-the-art deep learning techniques in terms of both learning efficiency and equal accuracy. .Using this real-time dataset, the proposed system achieves the highest accuracy of 97.93%.
Keywords: ATM, Face Recognition, Safety , Modules.
|
DOI:
10.17148/IJARCCE.2023.125261
