Author:
A. Dhivya ,K. Aashika ,S. Pavitha ,G. Varshini
Abstract
A crucial component of contemporary banking is now online banking. Due to the present password- based authentication paradigm’s inadequacies in terms of efficiency and robust, as well as their suspectibility to automated attacks, several attempts are successful in gaining access to social network accounts. The easiest solution is to add more identifying features, like one-time PIN numbers that are created by the user’s own device(like a smart phone) or sent to them via SMS to the single factor(Password-based) authentication procedure. With the help of this technology, client’s identities may be instantly and conveniently verified. The goal of this project is to create an online banking system that authenticates customer’s using real-time facial recognition technology. The system will be made to offer a safe and convenient user interface that enables users to perform financial operation like bill payment, money transfers, and balance queries. A facial recognition algorithm, such Grassmann learning, which can record and evaluate customer’s facial traits in real time, will be included into the system. To confirm customer’s identification, the algorithm will match the customer’s facial traits with those in the bank’s database. The technology would give users a safe and convenient interface to conduct real-time banking transactions. Notifications about banking amount transactions are sent to the user in this suggested netbanking application.
Reference10 articles.
1. Md Golam Mohiuddin, Avirup Chowdhury, Amogh Banerjee, Shalini Singh, Indrajit Das, Ria Das, and Amogh Banerjee. "Design and implementation of eye pupil movement based PIN authentication system." 2020 IEEE VLSI DCS (VLSI DEVICE CIRCUIT AND SYSTEM), pages 1-6. IEEE, 2020.
2. Jenny Domashova and Elena Kripak. "Identification of non-typical international transactions on bank cards of individuals using machine learning methods." 178–183 in Procedia Computer Science 190 (2021).
3. Natalia Mikhailina, Jenny Domashova, and others. "Usage of machine learning methods for early detection of money laundering schemes." 184–192 in Procedia Computer Science 190 (2021).
4. Alessio Merlo, Guerar, Meriem, Luca Verderame, Francesco Palmieri, and Mauro Migliardi. "Securing PIN‐based authentication in smartwatches with just two gestures." Practice and Experience with Concurrency and Computation 32, no. 18 (2020): e5549.
5. Kabir, M. Monjirul, Nasimul Hasan, Tanjil Ahmed Ovi, Md Khalid Hassan Tahmid, and Victor Stany Rozario, "Enhancing Smartphone lock security using vibration enabled randomly positioned numbers." In the International Conference on Computing Advancements Proceedings, 2020, pp. 1–7.