Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM68243
Volume:
10 |
10 |
Oct 2026
Pages:
1-3
Publication Frequency:
Monthly (12 issues per year)
License:International Journal of Scientific Research in Engineering and Management follows the Creative Commons Attribution 4.0 (CC BY 4.0) License, allowing free use and distribution with proper attribution.
Computer Science Engineering
East West Institute of Technology
Computer Science Engineering
East West Institute of Technology
Computer Science Engineering
East West Institute of Technology
Computer Science Engineering
East West Institute of Technology
This paper presents an Internet of Things (IoT)-based Smart Home Safety System that brings door access control, face verification, household-condition monitoring, and voice interaction into one web-based platform. The prototype uses an ESP32 to communicate with sensors and control a relay-driven 12 V solenoid lock. Face verification runs on a MacBook using its built-in camera, OpenCV Haar Cascade face detection, and Local Binary Patterns Histograms (LBPH) recognition; an ESP32-CAM is not used. The system also includes PIN-based authentication, a Flask backend, a MySQL database, a web dashboard, and NOVA, a voice assistant powered by OpenAI. A DHT11 measures temperature and humidity, a PIR sensor detects motion, a reed switch monitors the door, and gas/safety readings are checked against a configured threshold. The backend handles application requests and stores user records, sensor data, access logs, door events, and alerts. In functional testing, a registered face was recognized and the software reported the door-unlock action. The prototype demonstrates how IoT hardware, computer vision, database-backed services, and voice interaction can work together. However, its dependence on the MacBook and network services, along with the lack of advanced liveness detection, limits its readiness for real-world deployment.
KEYWORDS
This paper presented an IoT-based Smart Home Safety System with Image Verification. It combines ESP32-based sensor communication and door control with face verification, PIN-based authentication as outlined in the project design, a Flask backend, MySQL storage, a web dashboard, and the NOVA voice assistant powered by OpenAI. The final face-recognition setup uses the MacBook’s built-in camera rather than an ESP32-CAM. In the reported functional test, a registered face was verified and the unlock workflow completed. The prototype demonstrates the practical value of combining access control, home-condition monitoring, and voice interaction in one application. Future work should focus on more independent operation, stronger anti-spoofing, secure communication and credential handling, calibrated safety sensing, backup power, and systematic testing under different network and environmental conditions.
1. P. Viola and M. J. Jones, “Rapid Object Detection using a Boosted Cascade of Simple Features,” in Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), vol. 1, pp. I-511–I-518, 2001, doi: 10.1109/CVPR.2001.990517. 2. T. Ahonen, A. Hadid, and M. Pietikäinen, “Face Description with Local Binary Patterns: Application to Face Recognition,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 28, no. 12, pp. 2037–2041, Dec. 2006, doi: 10.1109/TPAMI.2006.244. 3. Pallets Projects, “Flask Documentation.” [Online]. Available: https://flask.palletsprojects.com/en/stable/. [Accessed: Oct. 21, 2026]. 4. Oracle, “MySQL Documentation.” [Online]. Available: https://dev.mysql.com/doc/. [Accessed: Oct. 21, 2026]. 5. OpenAI, “API Documentation.” [Online]. Available: https://platform.openai.com/docs/. [Accessed: Oct. 21, 2026]. 6. OpenCV, “OpenCV Documentation.” [Online]. Available: https://docs.opencv.org/. [Accessed: Oct. 21, 2026]. 7. Espressif Systems, “ESP32 Documentation.” [Online]. Available: https://docs.espressif.com/. [Accessed: Oct. 21, 2026].
Publication Date
10/23/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
1
Total views since publication
PDF Downloads
4
Total downloads since publication
Geographic Reach
5
Digital Preservation: This article is permanently archived on Zenodo and complies with all data preservation standards across major indexing platforms.
Plagiarism Screening
This manuscript has been checked for plagiarism using TurnitinPlagiarismChecker software.
Conflict of Interest
The authors declare no conflict of interest related to this research work.
Funding Information
No funding information available for this research.
Related research in the same subject area
Loading similar articles...