Detection of Ripeness in Oil Palm Fresh Fruit Bunches Using the YOLO12S Algorithm on Digital Images
DOI:
https://doi.org/10.30871/jaic.v9i4.10250Keywords:
Deep Learning, FFB Ripeness, Object Detection, Oil Palm, YOLO12sAbstract
Indonesia is the world's largest producer of palm oil, with a production volume reaching 46.82 million tons in 2022. This industry heavily relies on the quality of Fresh Fruit Bunches (FFB) harvests, which is determined by the accuracy of ripeness at the time of harvest. Unfortunately, ripeness assessment of FFB is still conducted manually and subjectively by field workers, posing risks to both efficiency and production accuracy. Although various studies have employed YOLOv5 and YOLOv8 for fruit ripeness detection, few have explored the potential of YOLO12s in classifying FFB ripeness in a comprehensive and efficient manner. In this study, we present the application of the YOLO12s algorithm to automatically classify the ripeness levels of oil palm FFB using digital images. The YOLO12s model was trained on 14,620 FFB images categorized into four ripeness levels: unripe, under-ripe, ripe, and overripe. Evaluation results showed a precision of 93.1%, recall of 95.9%, [email protected] of 97.8%, and [email protected]–0.95 of 78.8%. The model was able to perform inference in approximately 4.7 milliseconds per image and demonstrated good generalization despite challenges related to varying lighting conditions. These results indicate that YOLO12s holds great potential to replace subjective manual methods with a more accurate, consistent, and efficient classification solution to support the harvesting process in the palm oil industry.
Downloads
References
[1] Outlook Kelapa Sawit. Jakarta: Pusat Data dan Sistem Informasi Pertanian, 2024.
[2] B. P. Statistik, “Produksi Tanaman Perkebunan (Ribu Ton), 2023,” 2 May 2024. Accessed: Jun. 21, 2025. [Online]. Available: https://www.bps.go.id/id/statistics-table/2/MTMyIzI=/produksi-tanaman-perkebunan.html
[3] E. F. Himmah, M. Widyaningsih, and M. Maysaroh, “Identifikasi Kematangan Buah Kelapa Sawit Berdasarkan Warna RGB Dan HSV Menggunakan Metode K-Means Clustering,” J. Sains dan Inform., vol. 6, no. 2, pp. 193–202, 2020, doi: 10.34128/jsi.v6i2.242.
[4] J. Zulkarnain, Kusrini, and T. Hidayat, “Klasifikasi Tingkat Kematangan Tandan Buah Segar Kelapa Sawit Menggunakan Pendekatan Deep Learning,” JST (Jurnal Sains dan Teknol., vol. 12, no. 3, pp. 748–758, 2024, doi: 10.23887/jstundiksha.v12i3.59140.
[5] M. Y. M. A. Mansour, K. D. Dambul, and K. Y. Choo, “Object Detection Algorithms for Ripeness Classification of Oil Palm Fresh Fruit Bunch,” Int. J. Technol., vol. 13, no. 6, pp. 1326–1335, 2022, doi: 10.14716/ijtech.v13i6.5932.
[6] R. Kurniawan, A. T. Martadinata, and S. D. Cahyo, “Klasifikasi Tingkat Kematangan Buah Sawit Berbasis Deep Learning dengan Menggunakan Arsitektur Yolov5,” J. Inf. Syst. Res., vol. 5, no. 1, pp. 302–309, 2023, doi: 10.47065/josh.v5i1.4408.
[7] A. Ritonga, A. A. Munawar, and I. S. Nasution, “Klasifikasi Kematangan Tandan Buah Segar Kelapa Sawit (Elaeis gueneensis Jacq)menggunakan Pengolahan Citra Digital,” J. Ilm. Mhs. Pertan., vol. 8, no. 3, pp. 437–445, 2023.
[8] N. J. Hayati, D. Singasatia, and M. R. Muttaqin, “Object Tracking Menggunakan Algoritma You Only Look Once (YOLO)v8 untuk Menghitung Kendaraan,” Komputa J. Ilm. Komput. dan Inform., vol. 12, no. 2, pp. 91–99, 2023, doi: 10.34010/komputa.v12i2.10654.
[9] T. M. Banhazi and M. Tscharke, “A brief review of the application of machine vision in livestock behaviour analysis,” J. Agric. Informatics, vol. 7, no. 1, pp. 23–42, 2016, doi: 10.17700/jai.2016.7.1.279.
[10] F. Gusnanto, N. Rahaningsih, R. D. Dana, T. Informatika, and K. Cirebon, “Optimasi Model Klasifikasi Tingkat Kematangan Buah Mangga Dengan Metode Yolo11,” JATI (Jurnal Mhs. Tek. Inform., vol. 9, no. 1, pp. 1773–1780, 2025, doi: doi.org/10.36040/jati.v9i1.12591.
[11] S. Aras, P. Tanra, and M. Bazhar, “Deteksi Tingkat Kematangan Buah Tomat Menggunakan YOLOv5,” MALCOM Indones. J. Mach. Learn. Comput. Sci., vol. 4, no. 2, pp. 623–628, 2024, doi: 10.57152/malcom.v4i2.1270.
[12] A. Wibowo, L. Lusiana, and T. K. Dewi, “Implementasi Algoritma Deep Learning You Only Look Once (YOLOv5) Untuk Deteksi Buah Segar Dan Busuk,” Paspalum J. Ilm. Pertan., vol. 11, no. 1, p. 123, 2023, doi: 10.35138/paspalum.v11i1.489.
[13] Z. Genoveva and R. D. Syah, “Model Machine Learning Untuk Deteksi Tingkat Kematangan Tandan Buah Segar Kelapa Sawit Menggunakan MetodE,” J. Pertan. Presisi (Journal Precis. Agric., vol. 8, pp. 121–136, 2024, doi: http://dx.doi.org/10.35760/jpp.2024.v8i2.11848.
[14] D. S. Prasvita, M. M. Santoni, and N. Falih, “Deteksi Pohon Kelapa Sawit dengan Pendekatan Deep Learning pada Citra Multispectral di Indonesia,” Indones. J. Comput. Sci., vol. 13, no. 2, pp. 3111–3125, 2024, doi: 10.33022/ijcs.v13i2.3753.
[15] M. Gelar, S. Komputer, and U. M. Sorong, “Implementasi deep learning untuk deteksi umur berdasarkan citra wajah suku moi menggunakan metode yolo,” 2024.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Linnda Prawidya Nur'aini, Majid Rahardi
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:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License (Attribution-ShareAlike 4.0 International (CC BY-SA 4.0) ) 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 (See The Effect of Open Access).
