Pendeteksi Masker pada Gambar Menggunakan Model Deep Learning Yolo-v2 dengan ResNet-50
Abstract
Abstrak— Sistem deteksi masker merupakan suatu upaya untuk mencegah penyebaran COVID-19. Pada penelitian ini sistem deteksi masker dikembangkan menggunakan model deep learning Yolo-v2 dengan bantuan ResNet-50. ResNet-50 digunakan sebagai backbone layer pengganti Yolo-v2, sedangkan Yolo-v2 menjadi komponen utama pendeteksi face mask. Penelitian ini menggunakan Face Mask Dataset dan Medical Mask Dataset berupa citra gambar yang diambil dari kaggle. Pengujian parameter konfigurasi saat training model dilakukan dengan harapan dapat meningkatkan akurasi dan kinerja dari sistem deteksi masker. Sistem deteksi masker menggunakan metode ini mendapatkan hasil F1-Score sebesar 84%.
Kata Kunci — deteksi masker, ResNet-50, YOLO-v2, COVID-19
Downloads
References
https://www.who.int/indonesia/news/novelcoronavirus/qa/qa- how-is-covid-19-transmitted (accessed Jan. 31, 2023).
World Health Organization,
December 2020,= World Health Organization, WHO/2019-nCoV/IPC_Masks/2020.5, 2020.
Accessed: Jan. 31, 2023. [Online]. Available: https://apps.who.int/iris/handle/10665/337199
D. G. Lowe,
Computer Vision, Sep. 1999, vol. 2, pp. 1150- vol.2. doi: 10.1109/ICCV.1999.790410.
D. G. Lowe,
R. Girshick, J. Donahue, T. Darrell, and J. Malik,
Object Detection and Semantic Segmentation,= presented at the Proceedings of the IEEE Conference on Computer Vision and Pattern
Recognition, 2014, pp. 580-587. Accessed: Jan.
, 2023. [Online]. Available: https://openaccess.thecvf.com/content_cvpr_201
/html/Girshick_Rich_Feature_Hierarchies_201 _CVPR_paper .html
R. Girshick, "Fast R-CNN," presented at the Proceedings of the IEEE International Conference on Computer Vision, 2015, pp. -1448. Accessed: Jan. 31, 2023. [Online].
Available: https://openaccess.thecvf.com/content_iccv_201
/html/Girshick_Fast_RCNN_ICCV_2015_paper.html
S. Ren, K. He, R. Girshick, and J. Sun,
R-CNN: Towards Real-Time Object Detection with Region Proposal Networks,= in Advances in Neural Information Processing Systems, , vol. 28. Accessed: Jan. 31, 2023.
[Online]. Available: https://proceedings.neurips.cc/paper/2015/hash/
bfa6bb14875e45bba028a21ed38046-
Abstract.html
J. Redmon, S. Divvala, R. Girshick, and A. Farhadi,
[Online]. Available: https://www.cvfoundation.org/openaccess/content_cvpr_2016/h
tml/Redmon_You_Only_Look_CVPR_2016_pa per.html
J. Redmon and A. Farhadi, "YOLO9000: Better, Faster, Stronger," presented at the Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 7263-7271. Accessed: Jan. 31, 2023. [Online].
Available: https://openaccess.thecvf.com/content_cvpr_201
/html/Redmon_YOLO9000_Better_Faster_CV
PR_2017_paper.html
Y. Lee, C. Lee, H.-J. Lee, and J.-S. Kim,
Detection of Objects Using a YOLOv3 Network for a Vending Machine,= in 2019 IEEE International Conference on Artificial
Intelligence Circuits and Systems (AICAS), Mar., pp. 132-136. doi: 1109/AICAS.2019.8771517.
W. Liu et al.,
M. Loey, G. Manogaran, M. H. N. Taha, and N. E. M. Khalifa,
, p. 102600, Feb. 2021, doi: 1016/j.scs.2020.102600.
B. Mandal, A. Okeukwu, and Y. Theis,
model,= Neuroscience Informatics, vol. 2, no. 3, p. 100035, Sep. 2022, doi: 1016/j.neuri.2021.100035.
