International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 11 Issue: 12 | Dec 2024
p-ISSN: 2395-0072
www.irjet.net
Bank Locker Security System Using Machine Learning Samiksha Wagaj1, Vaishnavi Gund2, Sonali Mane3, Divya Sapkal4, prof.I.Y.Inamdar5, Prof.S.D.Pandhare6 1Student, Dept. of Computer Science & Eng., SMSMPITR, Akluj, Mharashtra, India 2Student, Dept. of Computer Science & Eng., SMSMPITR, Akluj, Mharashtra, India 3Student, Dept of Computer Science & Eng., SMSMPITR, Akluj, Mharashtra, India 4Student, Dept of Computer Science & Eng., SMSMPITR, Akluj, Mharashta, India
5Professor, Dept. of Computer Science & Eng., SMSMPITR, Akluj, Mharashtra, India
6Head of Department, Dept. of Computer Science & Eng., SMSMPITR, Akluj, Mharashtra, India
---------------------------------------------------------------------***---------------------------------------------------------------------
Abstract - This research proposes a robust bank locker
relying on physical locks, keys, and surveillance cameras, are becoming increasingly vulnerable to sophisticated security threats and human error. To address these challenges, machine learning (ML) has emerged as a promising solution to enhance and automate locker security. By leveraging ML algorithms, banks can develop intelligent systems capable of detecting anomalies, recognizing patterns in access behavior, and even predicting potential security breaches before they occur. [2]. Bank locker security is a critical aspect of safeguarding valuable assets and sensitive documents stored by customers in financial institutions. Traditional security measures, such as PIN codes, passwords, and physical keys, have proven to be vulnerable to various types of attacks, including unauthorized access, fraud, and social engineering. In light of these challenges, integrating machine learning (ML), face detection, and OTP (One-Time Password) authentication offers a robust and multi-layered security approach that significantly enhances the protection of bank lockers. [3]. By incorporating face detection, banks can leverage biometric authentication, ensuring that only authorized users gain access to lockers based on the unique features of their faces. This biometric factor provides a highly secure method of user identification, minimizing the risks associated with stolen credentials or impersonation attempts. Additionally, OTP authentication introduces a second layer of protection by verifying that the individual attempting access has the correct time-sensitive code sent to their registered mobile device or email. [4]. Through machine learning, the system can continuously learn user behavior patterns, detect anomalies in real-time, and adapt to evolving security threats. For example, ML models can identify abnormal login attempts, flag suspicious behaviors such as multiple failed authentication attempts, or recognize attempts to access the locker from unusual locations or devices. [5].
security system integrating machine learning with face detection and OTP authentication. The system utilizes a stateof-the-art face recognition algorithm to accurately identify authorized users, ensuring that only legitimate individuals can access their lockers. This research is used for bank because when the customer comes to bank to deposit his valuables in the bank locker for the security of the locker and we have used face recognition and one time password through machine learning to check whether the customer who came is real or not. Using face recognition for bank locker security has made it easier to identify authorized persons, Because we have used two factor authentication i.e. one time password message is sent to the authorized person's phone so high security is for bank lockers. Bank locker security using machine learning with face detection and OTP authentication it is very useful for bank and high security for bank lockers. Key Words: Face Detection, OTP Authentication, Machine Learning, etc.
1.INTRODUCTION The In recent years, the importance of security in banking and financial institutions has escalated, with physical and digital threats evolving in complexity. A critical component of bank security is the protection of locker systems, which store valuable items such as documents, jewelry, and other assets. Traditional methods of accessing these lockers, such as physical keys or PIN-based systems, can be vulnerable to theft, human error, or unauthorized access. As a result, the banking sector is increasingly looking toward more advanced technologies, such as machine learning, biometrics, and multi-factor authentication (MFA), to enhance the security of their locker systems. One such innovative approach is the integration of face detection technology with One-Time Password (OTP) authentication, powered by machine learning.[1].This combined approach aims to provide a robust, user-friendly, and highly secure system for accessing bank lockers. Bank locker security is a critical component of modern financial institutions, as it protects valuable assets and confidential documents from theft and unauthorized access. Traditional security systems,
© 2024, IRJET
|
Impact Factor value: 8.315
|
ISO 9001:2008 Certified Journal
|
Page 84