project presentation about enhanced security for atm machine and otp with shuffle features

it is about our final year presentation of BE AIDS department

1. ENHANCED SECURITY FOR ATM MACHINE WITH FACIAL RECOGNITION AND OTP WITH SHUFFLE KEYPAD FEATURES Omkar babar Shubham Veer Pratik Babar Omkar Dalvi Department of Artificial Intelligence and Data Science Suman Ramesh Tulsiani Charitable Trust’s Suman Ramesh Tulsiani Technical Campus Faculty of Engineering Kamshet, Pune Name of the Project Guide ( Color: Black, Font: Franklin Gothic Medium, Size 18) Dr.Vishal Puri Project Coordinator Prof. Dr. D.E. Upasani Head of the Department

2. Introduction Presently, ATM systems use no more than an access card which usually has a magnetic stripe (magstripe) and a fixed Personal Identification Number (PIN) for identity verification. Some other cases utilize a chip and a PIN which sometimes has a magstripe in case the chip fails as a backup for identification purposes. This method is not very secure and prone to increase in criminal activities. The need for a novel, simple as well as secure method of access is thus imperative. In the present work, a PIN is generated by the user and this PIN is made available to the ATM system by the means of a Subscriber Identity Module (SIM) in the user's Mobile Phone. This PIN can be trapped by any user and can be lead to fraud.

3. Literature Review Author Title Year A Kowshika, P.Sumathi , K S Sandra Facepin: Face Biometric Authentication System for Atm Using Deep Learning 2022 Asst. Prof. Borude K M,Aditya Gaikwad,Vaishnavi Bundele,Diksha Borade Enhance the Security of ATM Machine Access with Face and Fingerprint Recognition 2024 A.D. Gujar, N.BSawant, T.LHake Face Recognition Open CVBasedATM Security System. 2023

4. Blocked Diagram

5. Proposed Methodologies Only authorized person can access the Account using Face Detection. Guest User can access the Account using OTP and Shuffle Keyword. Fraud person cannot access the Account

6. Proposed Methodologies In order to provide reliable security solution to the people, the concept of ATM security system based on face detection is emerged. The Area of work is basically focused on Design and Implementation of Face Detection based ATM Security System using LRR algorithm. Limitations of existing system are overcome in our proposed system. In order to make any transaction, system will provide to option to process. First Self user, where in system will ask for “Detect Face” and allow to process transaction if it matches with Image store in banks database otherwise system will decline the transaction after couple of warnings.

7. HW/ SW Requirement As we are using Machine Learning Algorithm and Various High Level Libraries Laptop RAM minimum required is 8 GB. Hard Disk : 40 GB minimum 40 GB Hard Disk memory is required. Processor : Intel i5 Processor

8. HW/ SW Requirement Highly specified Programming Language for Machine Learning because of availability of High Performance Libraries. Operating System : Windows 10 Latest Operating System that supports all type of installation and development Environment

9. Proposed work in 2nd Semester Development : Develop a functional of Enhanced security for ATM machine with facial recognition and otp with shuffle keypad features To validate the proposed features and gather also user feedback Refinement: After the successful development, enhancing the GUI interface. Optimization : Optimization to avoid crashes, errors and for optimal facial recognition

10. References [1] Surawse, P., Bhange, Taru, S., Khot, S., & Mundada, Prof. J. (2022, February). Secure ATM Transactions Using Face Recognition & OTP, 2022JETIR February 2022, Volume 9, ISSN-2349-5162 [2] M. T. H. Fuad et al., "Recent Advances in Deep Learning Techniques for Face Recognition," in IEEE Access, vol. 9, pp. 99112-99142, 2021, doi:10.1109/ACCESS.2021.3096136 [3] Y. Martínez-Díaz, H. Méndez-Vázquez, L. S. Luevano, M. Nicolás-Díaz, L. Chang and M. GonzálezMendoza, "Towards Accurate and Lightweight Masked Face Recognition: An Experimental Evaluation," in IEEE Access, vol. 10, pp. 7341-7353, 2022, doi: 10.1109/ACCESS.2021.3135255. [4] P. Terhörst, M. Huber, N. Damer, F. Kirchbuchner, K. Raja and A. Kuijper, "Pixel-Level Face Image Quality Assessment for Explainable Face Recognition," in IEEE Transactions on Biometrics,Behavior, and Identity Science, vol. 5, no. 2, pp. 288-297, April 2023, doi:10.1109/TBIOM.2023.3263186.

11. References THANK YOU