Journal of Computers, Mechanical and Management

Rights and permissions

© The Author(s) 2025.

Open Access

This article is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License, which permits the non-commercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as appropriate credit to the original author(s) and the source is given by providing a link to the Creative Commons License and changes need to be indicated if there are any. The images or other third-party material in this article are included in the article's Creative Commons License, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons License and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this License, visit: httpshttps://creativecommons.org/licenses/by-nc/4.0/

S. Asane, S. S. Salve, A. Potdar, A. Wagh, M. Nilwarn, Security system using face recognition: machine learning based approach, Journal of Information and Communications Technology: Algorithms, Systems and Applications, 2025, 1(1), 25304, doi: https://doi.org/10.64189/ict.25304.

Abstract

The rising occurrences of illegal entry and security breaches have made guaranteeing safety inside residential societies a key worry in the contemporary day. Often lacking in consistent and tamperproof access control are traditional security solutions like manual guarding, RFID cards, or keypad locks. These traditional approaches are vulnerable to human error, duplication, and illegal use, hence stressing the critical need for a more smart and automated solution. Recent studies in the area of machine learning and computer vision have produced encouraging findings in facial recognition technologies. Many current methods, meanwhile, are costly, lack real-time processing, or need highend computing equipment. Research suggests building a Society Security System Using Face Recognition Technique and Machine Learning to solve these issues, with the goal of producing a lowcost, efficient, and frictionless access control system. Reducing dependence on manual monitoring, research intends to develop a scalable and efficient solution for community- level security systems that offers a more safe and automated access control system. Using a facial recognition model coupled with Support Vector Machine (SVM) classification, the proposed security system accurately identifies authorised faces. Testing on a dataset of authorised and unauthorized individuals revealed an overall accuracy of 95%. The model showed good real-time performance, fast response time, and resilience to changing lighting conditions and facial emotions. Attempts at unauthorized access were efficiently spotted and denied, hence guaranteeing improved security. The time delay between the Email notification is 3-4 sec and false acceptance rate is 3-5% it depends on threshold. The face detection time is 3-4 sec but it mainly gets affected by the network conditions. Servo operation time is 5 sec.

Graphical Abstract

Novelty statement

Using a facial recognition model coupled with Support Vector Machine (SVM) classification, the proposed security system accurately identifies authorised faces.