Open Access Open Access  Restricted Access Subscription Access

Autonomous Thermal Screening and Integrated Attendance Cataloguing System Using Machine Learning and Sqlite3

Simran Pal, Sonam Dorji, Sonu Kumar, Sunil Nagar, Surankan Chakraborty

Abstract


The concern toward health regulations has been on high alert since the Covid pandemic. Almost all public places necessitate a thermal checkup at the entrances. This research aims to create an economic and reliant camera ecosystem, which is automated and integrated to detect individuals by their pre-recorded facial biometrics, check their heat signature against a threshold, and log that as attendance in a database with the hash of said individual. The present systems are either too expensive or unreliable if it's affordable. The research proposes a relatively inexpensive solution that is easy to implement and flexible. The most ergonomic algorithms available are selected and used to increase detection accuracy: Dlibs' facial recognition model, Haar Cascade SVM, and DNN are some primary algorithms used. The most costly component of the existing systems is the thermal sensors, and the research addresses this issue using OpenCV's library methods, which are cheap to implement and use. The proposed system will work in real time with dynamic image recognition.


Full Text:

PDF

References


Mushahar, M.F., and Zaini, N. (2021) “Human body temperature detection based on thermal imaging and screening using Yolo Person Detection,” 2021 11th IEEE International Conference on Control System, Computing and Engineering (ICCSCE) [Preprint]. Available at: https://doi.org/10.1109/iccsce52189.2021.9530864

Ramya, Y. et al. (2022) “A novel attendance system based on face recognition using Haar-cascade and SVM,” 2022 4th International Conference on Smart Systems and Inventive Technology (ICSSIT) [Preprint]. Available at: https://doi.org/10.1109/icssit53264.2022.9716423.

Winahyu, H.S., Wardihani, E.D. and Beta, S. (2021) “Attendance system based on face recognition, face mask and body temperature detection on Raspberry Pi,” 2021 International Seminar on Application for Technology of Information and Communication (semantic) [Preprint]. Available at: https://doi.org/10.1109/isemantic52711.2021.9573182.

Zhang, D., Li, J. and Shan, Z. (2020) “Implementation of Dlib deep learning face recognition technology,” 2020 International Conference on Robots & Intelligent Systems (ICRIS) [Preprint]. Available at: https://doi.org/10.1109/icris52159.2020.00030.

Praveena, M., Srinija, K.G. and Meghana, A. (2022) “Perception of age and gender detection by using hierarchical deep learning architecture through vision,” 2022 International Conference on Sustainable Computing and Data Communication Systems (ICSCDS) [Preprint]. Available at: https://doi.org/10.1109/icscds53736.2022.9760865

WU Jinyi,ZHOU Delong. A survey of face recognition methods[J]. Computer Application Research, 2019,26(9):3205-3209

LI Yuelong, JIN Ya, et al. A survey of face feature point extraction methods [J]. Journal of Computer Science. 2016,39(7):1356-1374

D. Bhattacharyya, R. Ranjan, F. A. a, dan M. Choi, “Biometric Authentication : A Review,” Int. J. Serv. Sci. Technol., vol. 2, no. 3, hal. 13–28, 2009.

M. Alhothaily, M. Alradaey, M. Oqbah, dan A. El-Kustaban, “Fingerprint Attendance System for Educational Institutes,” J. Sci. Technol., vol. 20, no. 1, hal. 34–44, 2015, doi: 10.20428/jst.20.1.4.

O. O. Mikail dan B. U. Umar, “Design and Development of a Fingerprint Door,” no. May, 2018. Https://www.solution.co.id/, “Fingerprint Time Attendance - Face Identification - RFID - Mifare.” [Daring]. Tersedia pada: https://www.solution.co.id/en/c1.php. [Diakses: 28-Jan-2020].


Refbacks

  • There are currently no refbacks.