EFEK SINERGIS IMAGE RECOGNITION PADA MODULAR PRODUCTION SYSTEM UNTUK MENDETEKSI KEMASAN RUSAK
DOI:
https://doi.org/10.35457/quateknika.v16i01.5671Keywords:
YOLOv8, image recognition , Raspberry Pi, Arduino, deteksi cacat, kemasanAbstract
Penelitian ini bertujuan untuk merancang dan mengimplementasikan sistem deteksi cacat kemasan minuman secara otomatis menggunakan algoritma You Only Look Once version 8 (YOLOv8). Sistem ini dibangun menggunakan kamera webcam untuk akuisisi citra, Raspberry Pi atau laptop sebagai pusat pemrosesan, serta Arduino untuk mengendalikan proses penyortiran kemasan berdasarkan hasil deteksi. Dataset citra kemasan diperoleh melalui pengambilan gambar langsung di jalur conveyor, kemudian diberi label menggunakan perangkat lunak Label Studio. Model YOLOv8 dilatih untuk mengenali dua kategori objek, yaitu kemasan baik (good) dan rusak (damage). Proses deteksi dilakukan secara real-time dan hasil klasifikasi dikirim ke Arduino dalam bentuk sinyal logika untuk mengaktifkan micro servo dalam proses sortir. Hasil pengujian menunjukkan bahwa sistem mampu melakukan deteksi dan penyortiran secara otomatis dengan tingkat akurasi sebesar 80% pada Raspberry Pi dan meningkat hingga ±95% saat dijalankan menggunakan laptop. Sistem dinilai layak sebagai prototipe edukatif dan memiliki potensi untuk dikembangkan lebih lanjut dalam implementasi industri berskala kecil hingga menengah.
Downloads
References
[1] J. Ekonomi, K. Indonesia, R. Prayuda, and S. Hadi, “IMPLEMENTASI PENGENDALIAN KUALITAS
PADA UKM :,” vol. 2, no. 3, pp. 178–194, 2024.
[2] P. Constante, O. Chang, E. Pruna, and I. Escobar, “Artificial Vision Techniques for Strawberry ’ s
Industrial Classification,” vol. 14, no. 6, pp. 2576–2581, 2016.
[3] P. Standardisasi, “IKM KUAT dengan PENERAPAN STANDARDISASI”.
[4] R. C. Gonzalez and R. E. Woods, Digital Image Processing, 4e.
[5] J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, “You Only Look Once : Unified , Real-Time Object
Detection,” 2016, doi: 10.1109/CVPR.2016.91.
[6] “6. Raspberry_Pi_The_Complete_Manual_8th_Ed_2016.pdf.”
[7] B. Rampai, METODOLOGI PENELITIAN Akuntansi Dan Manajemen Pendekatan Kuantitatif.
[8] Arduino, “Arduino Uno Board Overview,” 2022. https://www.arduino.cc.
[9] B. G. Bradski, “The OpenCV Library,” no. 11.
[10] R. Ruelas, “Vision System Prototype for Inspection and Monitoring with a Smart Camera,” vol. 18, no.
9, pp. 1614–1622, 2020.
[11] “Proximity Sensor / Switch,” pp. 1–5.
[12] J. Miguel, P. Mendonça, A. Quelhas, and M. L. P. Caldeira, “Using Computer Vision to Collect
Information on Cycling and Hiking Trails Users,” 2024.
[13] L. S. Martinez-rau, Y. Zhang, and G. S. Member, “On-device Anomaly Detection in Conveyor Belt
Operations,” pp. 1–14, 2025.
[14] C. Pan, Q. Tao, H. Pei, B. Wang, and W. Liu, “Belt conveyor idler fault detection algorithm based on
improved,” pp. 1–13, 2025.
[15] J. Informatika, D. A. N. Teknik, E. Terapan, J. Informatika, D. A. N. Teknik, and E. Terapan, Jurnal
informatika dan teknik elektro terapan, vol. 12. 2024.
[16] I. Fatahna, P. Desi, K. Sari, A. N. Kamilah, and R. Wulanningrum, “Implementasi Computer Vision
Terhadap Jenis Kualitas Pisang Susu Menggunakan Metode YOLOv8n Berbasis WebApps”.
[17] P. D. Sugiyono, METODE PENELITIAN KUANTITATIF KUALIFIKATIF DAN R&D.
[18] T. Vu, D. Pham, and T. Chang, “ScienceDirect ScienceDirect A YOLO-based Real-time Packaging
Defect Detection System,” Procedia Comput. Sci., vol. 217, no. 2022, pp. 886–894, 2023, doi:
10.1016/j.procs.2022.12.285.
[19] M. S. R. Muhammad Noorazlan Shah Zainudin, Muhammad Idzdihar Idris, Soh Jun Kang, Tan Ann Chee,
Teoh Yu Xian, Jamil Abedalrahim Jamil Alsayaydeh, Sufri Muhammad, “Analysis Detection of RealTime Metallic Surface Defect using MobileNetv2 and YOLOv3 on Raspberry Pi.”
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Jurnal Qua Teknika
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Copyright on any article is retained by the author(s).
- Author grant the journal, right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work’s authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal’s published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
- The article and any associated published material is distributed under the Creative Commons Attribution-ShareAlike 4.0 International License
Deprecated: json_decode(): Passing null to parameter #1 ($json) of type string is deprecated in /home/ejournal.unisbablitar.ac.id/public_html/plugins/generic/citations/CitationsPlugin.php on line 68
