Arc Circularitie Naive Bayes for Occupational Safety Helmet Detection

Abstract

Occupational Safety and Health (OHS) is an effort to guarantee and protect the safety and health of every worker through efforts to prevent work accidents and work-related diseases. Safety Helmet is one of the components that must exist and be used in accordance with Occupational Safety and Health standards. Detection of safety helmets usage is one of the efforts to support these activities. The application of Arc Circularity Naive Bayes is used to detect whether an object meets the ratio of a circle by utilizing RGB and HSV image filtering and classification using Naïve Bayes. That method is used to detect whether a worker uses a safety helmet or not, it also detects helm color. The average value of accuracy is 50.8, precision is 58.3%, recall is 66.0%, and f1-score is 59.5% which are calculated using the Confusion Matrix

Keywords

Arc Circularitie; Helmet; Image Processing; Naïve Bayes; OHS

Full Text:

Article (PDF) Check plagiarism (PDF)

References

Y. Adiratna, S. Astono, M. Fertiaz, S. C. A. O. Sugistria, H. Prayitno, R. I. Khair, A. Brando e B. A. Putri, Profil Keselamatan Dan Kesehatan Kerja Nasional Indonesia Tahun 2022, Jakarta: Kementerian Ketenagakerjaan Republik Indonesia, 2022.

A. K. Wijaya e S. Devella, “Pengenalan Penggunaan Helm Proyek Berstandar Pada Citra Foto Berdasarkan SIFT Dengan SVM,” Jurnal Ilmiah Teknologi dan Komputer, vol. 3, nº 2, 2022.

Z. Fangbo, Z. Huailin e N. Zhen, “Safety Helmet Detection Based on YOLOv5,” em International Conference on Power Electronics, Computer Applications (ICPECA), Shenyang, China, 2021.

S. Firdiyan e H. Hasti, “Deteksi Helm Keselamatan Kerja Barbasis Android Menggunakan Metode PCA (Component Principal Analys),” Jurnal Dinamika Informatika, vol. 10, nº 2, p. 84–90, 2021.

S. E. Setyati e H. Armanto, “Deteksi Alat Pelindung Kepala (Helm) Menggunakan Metode Haar Cascade Classifier,” Journal of Informatic Unisla, vol. 4, nº 1, 2019.

N. J. Peksi, B. Yuwono e M. Y. Florestiyanto, “Classification of Anemia with Digital Images of Nails and Palms using the Naive Bayes Method,” Telematika: Jurnal Informatika dan Teknologi Informasi, vol. 18, nº 1, pp. 118-130, 2021.

M. M. H. Santoso e R. Muliono, “Analysis Naïve Bayes In Classifying Fruit by Utilizing Hog Feature Extraction,” Journal of Informatics and Telecommunication Engineering, vol. 4, nº 1, 2020.

R. Kosasih e A. Fahrurozi, “Pengklasifikasian Bunga Dengan Menggunakan Metode ISOMAP Dan Naive Bayes Classifier,” Jurnal Ilmiah Informatika dan Komputer, vol. 22, nº 3, 2017.

A. S. Talaulikar, S. Sanathanan e C. N. Modi, “An Enhanced Approach for Detecting Helmet on Motorcyclists Using Image Processing and Machine Learning Techniques,” em International Conference on Advanced Computing and Communication Technologies, 2018.

M. M. Saritas e A. Yasar, “Performance Analysis of ANN and Naive Bayes Classification Algorithm for Data Classification,” International Journal of Intelligent Systems and Applications in Engineering, vol. 7, nº 2, pp. 88-91, 2019.

R. R. V. e. Silva, K. R. T. Aires e R. d. M. S. Veras, “Detection of Helmets on Motorcyclists,” Multimed Tools Appl, vol. 77, 2018.

M. Hatami, T. Tukino, F. Nurapriani, W. Widiyawati e W. Andriani, “DETEKSI HELMET DAN VEST KESELAMATAN SECARA REALTIME MENGGUNAKAN METODE YOLO BERBASIS WEB FLASK,” Jurnal Pendidikan Sains dan Teknologi, vol. 10, nº 1, 2023.

S. D. , “ENERAPAN ALGORITMA NAÏVE BAYES UNTUK MENGETAHUI KUALITASPRODUKSI HELMET HONDA PADA PT TERANG PARTS INDONESIA,” Journal of Research and Publication Innovation, vol. 1, nº 3, 2023.

G. L. e T. Shilei, “Improved YOLOv5 Network Model and Application in Safety Helmet Detection,” em IEEE International Conference on Intelligence and Safety for Robotics (ISR), Tokoname, Japan, 2021.

R. C, X. H, Z. Z e Z. W, “Multi-Scale Safety Helmet Detection Based on SAS-YOLOv3-Tiny,” Applied Sciences, vol. 11, nº 8, 2021.

http://dx.doi.org/10.28989/compiler.v12i2.1760

Article Metrics

Abstract view: 220 times
Download     : 135   times Download     : 28   times

This work is licensed under a Creative Commons Attribution 4.0 International License.

Refbacks

• There are currently no refbacks.