Intruder Detection Management System Using Face Recognition Mask Detection & Motion Detection

In conclusion, the proposed Intruder Detection Management System (IDMS) presents an effective and intelligent solution for enhancing security in modern residential and institutional environments. By integrating motion detection, face recognition, and mask detection technologies, the system provides a multi-layered approach to identifying and preventing unauthorized access. The use of Convolutional Neural Networks (CNN) ensures high accuracy in recognizing individuals and detecting mask compliance, while PIR sensors enable efficient and real-time activation of the system. The implementation using Raspberry Pi and IoT-based communication allows for automated access control, remote monitoring, and instant alert notifications, significantly improving response time and user convenience. Although minor challenges such as lighting variations and face occlusion exist, the overall system demonstrates strong performance, reliability, and scalability. Therefore, the proposed system serves as a cost-effective, secure, and practical solution for smart surveillance and intruder detection applications.

[1] Nabila, W. Priharti, and Istiqomah, “Design of Home Security System Using Face Recognition with Convolutional Neural Network Method,” 2022 IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology (IAICT), pp. 78-83.   [2] S. Bhatlawande, S. Shilaskar, T. Gadad, S. Ghulaxe, and R. Gaikwad, “Smart Home Security Monitoring System based on Face Recognition and Android Application,” 2023 International Conference on Intelligent Data Communication Technologies and Internet of Things (IDCIoT), pp. 222-225.   [3] K. B. Pranav and J. Manikandan, “Design and Evaluation of a Real-Time Face Recognition System using Convolutional Neural Networks,” Procedia Computer Science, vol. 171, pp. 1651-1659, 2020.   [4] D. Tribuana, H. Hazriani, and A. L. Arda, “Face recognition for smart door security access with convolutional neural network method,” TELKOMNIKA, vol. 22, no. 3, pp. 1234-1241, 2024.   [5] Khandaker Mohammad Mohi Uddin, "Home automation security system using IoT and AI for face recognition," International Journal of Engineering Research, 2023.   [6] Akshay H A, "Smart Door Security System using Facial Recognition and Raspberry Pi," International Research Journal of Engineering and Technology, vol. 8, 2021.   [7] Shilpa et al., "Data-efficient models for lung cancer detection using transfer learning," IEEE Access, 2024.   [8] Fu et al., "Multiscale feature extraction methods for tumor classification," Journal of Medical Imaging, 2025.   [9] JeyaMala et al., "Lightweight U-Net and 3D CNNs for medical image segmentation," Computers in Biology and Medicine, 2024.   [10] Chen et al., "Comparative study of hybrid deep learning models for medical imaging," Neural Computing and Applications, 2024.