Improving Palm Oil Production Efficiency through Deep Learning Algorithms for Fruit Ripeness Detection in Digital Images
Abstract
Oil palm is a strategic commodity in Indonesia, and its production quality is greatly influenced by the ripeness of the fruit at harvest. Manual ripeness determination is still subjective and prone to errors due to variations in worker experience and environmental conditions. Advances in computer vision and deep learning technology offer a more objective and consistent automated solution. This study aims to develop and evaluate a model for detecting the ripeness level of palm oil fruit using the YOLOv12m algorithm based on digital images. The dataset used consists of 3,375 images with three ripeness classes (unripe, semi-ripe, ripe), which are divided into training, validation, and testing data with a ratio of 70:20:10. The model was trained for a maximum of 25 epochs with an early stopping mechanism. The evaluation was conducted using precision, recall, mAP@50, and mAP@50–95 metrics. The results showed excellent performance with precision of 0.958, recall of 0.946, mAP@50 of 0.985, and mAP@50–95 of 0.882. Class-by-class analysis shows the best performance in the raw and ripe classes, while the unripe class still poses challenges due to visual similarities between transition phases. Overall, the YOLOv12m model has proven to be effective and has the potential to be applied as a more objective and efficient harvest decision support system.
Keywords
Full Text:
PDFReferences
Akbar, Arief Rahmad Maulana, Alan Dwi Wibowo, and Redi Santoso. “Investigation on the Optimal Harvesting Time of Oil Palm Fruit.” Jurnal Teknik Pertanian Lampung (Journal of Agricultural Engineering) 12, no. 2 (2023): 524. https://doi.org/10.23960/jtep-l.v12i2.524-532
Ge, Tianchen, Bo Ning, and Yiwu Xie. “YOLO-AFR: An Improved YOLOv12-Based Model for Accurate and Real-Time Dangerous Driving Behavior Detection.” Applied Sciences 15, no. 11 (2025): 6090. https://doi.org/10.3390/app15116090
Hariyanti, Fitri, Almasdi Syahza, Zulkarnain, and Nofrizal. “Economic Transformation Based on Leading Commodities through Sustainable Development of the Oil Palm Industry.” Heliyon 10, no. 4 (2024): e25674. https://doi.org/10.1016/j.heliyon.2024.e25674
Hasibuan, Achmad Alwi, Ali Amran Nst, Aldi Antoni, Ray Handika, Budi Yanto, and Akhmad Zulkifli. “Advanced Classification of Oil Palm Fruit Ripeness Using ResNet50 and Real-Time Image Analysis for Enhanced Agricultural Practices.” JOURNAL OF ICT APLICATIONS AND SYSTEM 3, no. 2 (2024): 75–84. https://doi.org/10.56313/jictas.v3i2.395
Hasibuan, Hasrul Abdi. “Penentuan Rendemen, Mutu Dan Komposisi Kimia Minyak Sawit Dan Minyak Inti Sawit Tandan Buah Segar Bervariasi Kematangan Sebagai Dasar Untuk Penetapan Standar Kematangan Panen.” Jurnal Penelitian Kelapa Sawit 28, no. 3 (2020): 123–32. https://doi.org/10.22302/iopri.jur.jpks.v28i3.106
Josdaan, Jordan, Vianna Calista Tamsil, Jeklin Harefa, and Kenny Jingga. “Revolutionizing Palm Oil Ripeness Classification: Utilizing YOLOv8 for Ultra-Precise Ripeness Detection.” Procedia Computer Science 245 (2024): 700–709. https://doi.org/10.1016/j.procs.2024.10.296
Lai, Jin Wern, Hafiz Rashidi Ramli, Luthffi Idzhar Ismail, and Wan Zuha Wan Hasan. “Oil Palm Fresh Fruit Bunch Ripeness Detection Methods: A Systematic Review.” Agriculture 13, no. 1 (2023): 156. https://doi.org/10.3390/agriculture13010156
Nur Rali Rahma Wati, Asrul Abdullah, and Sucipto Sucipto. “Klasifikasi Tingkat Kematangan Buah Kelapa Sawit Menggunakan Metode Convolutional Neural Network.” Jurnal Publikasi Teknik Informatika 4, no. 3 (2025): 273–85. https://doi.org/10.55606/jupti.v4i3.5841
Nur’aini, Linnda Prawidya, and Majid Rahardi. “Detection of Ripeness in Oil Palm Fresh Fruit Bunches Using the YOLO12S Algorithm on Digital Images.” Journal of Applied Informatics and Computing 9, no. 4 (2025): 1633–38. https://doi.org/10.30871/jaic.v9i4.10250
Rosbi, Munirah, Zaid Omar, Uswah Khairuddin, Anwar P. P. A. Majeed, and Syed A. R. S. A. Bakar. “Machine Learning for Automated Oil Palm Fruit Grading: The Role of Fuzzy C-Means Segmentation and Textural Features.” Smart Agricultural Technology 9 (December 2024): 100691. https://doi.org/10.1016/j.atech.2024.100691
Sudarti, Atrida, and Munirul Ula. Image Feature Extraction for Determining the Ripeness Level OF Oil Palm Fruits Using the K-Nearest Neighbor Algorithm Based on Color Features (Case PTPN IV Aceh Utara). 9, no. 158 (2025).
Suharjito, Franz Adeta Junior, Yosua Putra Koeswandy, et al. “Annotated Datasets of Oil Palm Fruit Bunch Piles for Ripeness Grading Using Deep Learning.” Scientific Data 10, no. 1 (2023): 72. https://doi.org/10.1038/s41597-023-01958-x
Yang, Zhaofeng, Zohaib Khan, Yue Shen, and Hui Liu. “GTDR-YOLOv12: Optimizing YOLO for Efficient and Accurate Weed Detection in Agriculture.” Agronomy 15, no. 8 (2025): 1824. https://doi.org/10.3390/agronomy15081824
Zulkarnain, Jefri, Kusrini, and Tonny Hidayat. “Klasifikasi Tingkat Kematangan Tandan Buah Segar Kelapa Sawit Menggunakan Pendekatan Deep Learning.” JST (Jurnal Sains Dan Teknologi) 12, no. 3 (2024). https://doi.org/10.23887/jstundiksha.v12i3.59140
DOI: https://doi.org/10.21107/pamator.v19i2.33569
Refbacks
- There are currently no refbacks.
Copyright (c) 2026 Tsabita Rosyidah Putri, i gede susrama mas diyasa, alfan rizaldy pratama
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Jurnal Pamator : Jurnal Ilmiah Universitas Trunojoyo by Universitas Trunojoyo Madura is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
