Application Of Yolo V8 For Product Defect Detection In Manufacturing Companies

Malikil Jamal; Sultan Faisal; Dwi Sulistya Kusumaningrum; Tatang Rohana

Authors

Malikil Jamal Universitas Buana Perjuangan Karawang
Sultan Faisal Universitas Buana Perjuangan Karawang
Dwi Sulistya Kusumaningrum Universitas Buana Perjuangan Karawang
Tatang Rohana Universitas Buana Perjuangan Karawang

Abstract

One important aspect in the production process is maintaining product quality and avoiding defects that could harm the company. This research aims to improve quality and avoid product defects that are detrimental to the company, especially defects in the form of bubbles in the product, by using YOLOv8. The dataset consists of 100 data which is divided into 80 for training and 20 testing data with an epoch value of 100. To obtain optimal bubble detection results, this research chose the latest version of YOLOv8 and compared several models, namely YOLOv8n, YOLOv8s, YOLOv8m, YOLOv8l, and YOLOv8x. The research results show that YOLOv8m achieves the highest accuracy among other models with a mAP value of 0.712, precision of 0.764, recall of 0.659, and F1-score of 0.708. This research highlights the potential of detection models that can detect bubbles precisely and accurately.

Keywords: Kecacatan Produk, Deteksi Gelembung, Perusahaan Manufaktur, Model YOLOv8

References

Aisya Putri Zanuarizqi. (2021). Analysis of Defective Product Control Using the Pdca Cycle on Cv. Yogyakarta Color House. Indonesian Islamic University Yogyakarta.

Aris Setiyadi, Ema Utami, & Dhani Ariatmanto. (2023). Analysis of the Capability of the YOLOv8 Algorithm in Detecting Human Objects Using the Architectural Modification Method. Journal of Computer Science & Informatics (J-SAKTI), 7(2).

Arther Sandag, G., Waworundeng Klabat University, J., Arnold Mononutu, J., & -North Minahasa, A. (nd). Identify Fashion Images Using Convolutional Neural Network (CNN) Identify Fashion Images Using Convolutional Neural Network (CNN). Cogito Smart Journal |, 7(2), 2021.

Guo, Z., Wang, C., Yang, G., Huang, & Li, G. (2022). MSFT-YOLO: Improved YOLOv5 Based on Transformer for Detecting Defects of Steel Surface. Censorship, 22(9). https://doi.org/10.3390/s22093467

Hayati, NJ, Singasatia, D., Muttaqin, MR, Informatika, T., Tinggi, S., & Wastukancana, T. (2023). Object Tracking Uses the You Only Look Once (Yolo) V8 Algorithm to Count Vehicles. KOMPUTA: Scientific Journal of Computers and Informatics, 12(2). https://universe.roboflow.com/

Horvat, M., Jelečević, L., & Gledec, G. (nd). A comparative study of YOLOv5 models performance for image localization and classification. https://www.researchgate.net/publication/363824867

Huang, J., Zeng, K., Zhang, Z., & Zhong, W. (2023). Solar panel defect detection design based on YOLO v5 algorithm. Heliyon, 9(8). https://doi.org/10.1016/j.heliyon.2023.e18826

Jayidan, Z., Mutoi Siregar, A., Faisal, S., & Hikmayanti, H. (2024). Improving Heart Disease Prediction Accuracy Using Principal Component Analysis (PCA) In Machine Learning Algorithms. Journal of Information Engineering (JUTIF), 5(3), 821–830. https://doi.org/10.52436/1.jutif.2024.5.3.2047

Julian, J., Daffa Ulhaq, F., Dewantara, AB, Hendra Purba, R., Wahyuni, F., & Junaedi, T. (2024). Microbubble Measurements using Image Processing with the YOLOv8 Comparison Model Introduction. Journal of Applied Science and Advanced Technology Journal Homepage. https://doi.org/10.24853/JASAT.6.3.109-116

Kiki Wahyuddin, Deden Wahiddin, & Dwi Sulistya Kusumaningrum. (2023). Door Security Face Detection System Using Arduino-Based Convolutional Neural Network (CNN) Method. Scientific Student Journal for Information, Technology and Science.

Maulana, A., Suherman, M., Masruriyah, AFN, & Novita, HY (2024). Application of the CNN Algorithm Using the Yolo Framework for Product Object Detection in Manufacturing Companies. INTI Nusa Mandiri, 18(2), 107–114. https://doi.org/10.33480/inti.v18i2.5028

Nur, M., Muhlashin, I., Stefanie, A., Universitas, S., Karawang, JH, Ronggo, W., & Karawang, I. (2023). Classification of Eye Diseases Based on Fundus Images Using Yolo V8. In Information Engineering Student Journal (Vol. 7, Issue 2).

Resti, J., Salsabilla Basuni, N., & Mutoi Siregar, A. (nd). Comparison of the Accuracy of Drug User Classification Models Using Machine Learning Methods. 5, 2026. https://doi.org/10.29207/resti.v7ix.xxx

Setia Pratama, F. (nd). SENOPATI Journal Sustainability, Ergonomics, Optimization, and Application of Industrial Engineering Product Defect Analysis using the Seven Tools Method and FTA by Considering Risk Values based on the FMEA Method.

Yoga Wibowo, M., Hikmayanti, H., Fitri Nur Masruriyah, A., Novalia, E., & Heryana, N. (2023). Article info Mask Use Detection in Public Places Using the Convolutional Neural Network Algorithm. In Edutran Computer Science and Information Technology (Vol. 1, Issue 1).