Pemanfaatan Google Colab Untuk Aplikasi Pendeteksian Masker Wajah Menggunakan Algoritma Deep Learning YOLOv7

Abstract
From a comprehensive review of facial mask detection techniques, there are several algorithms based on deep learning, namely You Only Look Once (YOLO), Single Shot Detector (SSD), RetinaFace, and (Faster Recurrent Convolutional Neural Network) Faster R-CNN. Previous studies focused on the detection accuracy of face masks using a two-stage detection model (ie, Faster R-CNN), while single-stage detectors (ie, YOLO) achieved fast inference times but lower accuracy. The training results in this study show that the Precision value is consistent at 0.4 – 0.8. While the maximum recall value is 0.6. Future research will focus on using YOLOv7 for other object detection.
Downloads
References
[2] R. A. S. Naseri, A. Kurnaz, and H. M. Farhan, “Optimized face detector-based intelligent face mask detection model in IoT using deep learning approach,” Appl Soft Comput, vol. 134, p. 109933, Feb. 2023, doi: 10.1016/j.asoc.2022.109933.
[3] Althaf Adhari Rachman and Ivan Maurits, “SISTEM DETEKSI PEMAKAIAN MASKER PADA WAJAH SECARA REAL TIME MENGGUNAKAN FRAMEWORK TENSORFLOW DAN LIBRARY OPENCV,” Jurnal Ilmiah Teknik, vol. 2, no. 1, pp. 49–59, Jan. 2023, doi: 10.56127/juit.v2i1.496.
[4] W. Zhu, H. Zhang, J. Eastwood, X. Qi, J. Jia, and Y. Cao, “Concrete crack detection using lightweight attention feature fusion single shot multibox detector,” Knowl Based Syst, vol. 261, p. 110216, Feb. 2023, doi: 10.1016/j.knosys.2022.110216.
[5] X. Fan and M. Jiang, “RetinaFaceMask: A Single Stage Face Mask Detector for Assisting Control of the COVID-19 Pandemic,” May 2020.
[6] S. Ren, K. He, R. Girshick, and J. Sun, “Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks,” IEEE Trans Pattern Anal Mach Intell, vol. 39, no. 6, pp. 1137–1149, Jun. 2017, doi: 10.1109/TPAMI.2016.2577031.
[7] N. D. T. Yung, W. K. Wong, F. H. Juwono, and Z. A. Sim, “Safety Helmet Detection Using Deep Learning: Implementation and Comparative Study Using YOLOv5, YOLOv6, and YOLOv7,” in 2022 International Conference on Green Energy, Computing and Sustainable Technology (GECOST), Oct. 2022, pp. 164–170. doi: 10.1109/GECOST55694.2022.10010490.
[8] S. Liu, Y. Wang, Q. Yu, H. Liu, and Z. Peng, “CEAM-YOLOv7: Improved YOLOv7 Based on Channel Expansion and Attention Mechanism for Driver Distraction Behavior Detection,” IEEE Access, vol. 10, pp. 129116–129124, 2022, doi: 10.1109/ACCESS.2022.3228331.
[9] S. Elfwing, E. Uchibe, and K. Doya, “Sigmoid-weighted linear units for neural network function approximation in reinforcement learning,” Neural Networks, vol. 107, pp. 3–11, Nov. 2018, doi: 10.1016/j.neunet.2017.12.012.
[10] T. Q. Vinh and N. T. N. Anh, “Real-Time Face Mask Detector Using YOLOv3 Algorithm and Haar Cascade Classifier,” in 2020 International Conference on Advanced Computing and Applications (ACOMP), Nov. 2020, pp. 146–149. doi: 10.1109/ACOMP50827.2020.00029.
[11] R. T. Handayanto and H. Herlawati, “Prediksi Kelas Jamak dengan Deep Learning Berbasis Graphics Processing Units,” Jurnal Kajian Ilmiah, vol. 20, no. 1, pp. 67–76, Jan. 2020, doi: 10.31599/jki.v20i1.71.

This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under an Attribution 4.0 International (CC BY 4.0) that allows others to share — copy and redistribute the material in any medium or format and adapt — remix, transform, and build upon the material for any purpose, even commercially with an acknowledgment of the work's authorship and initial publication in this journal.