Abstract—The ripeness of oil palm fresh fruit bunches significantly impacts the quality and economic value of palm oil production. This study proposes a novel approach using deep learning, particularly You Only Look Once (YOLO)v8, to classify and detect the ripeness of oil palm fruit bunches. By leveraging pretrained models and fine-tuning techniques, this study aims to improve detection accuracy while reducing inference time. The methodology involves data preparation, model training, and evaluation, utilizing a dataset comprising 427 images of oil palm fruit bunches classified into raw, half-ripe, and ripe categories. Additionally, the images were augmented to increase the dataset size. The YOLOv8 architecture, known for its scalability and efficiency, is applied to improve the classification process. Results demonstrate that YOLOv8 provides a balance between accuracy and processing speed, making it a suitable tool for real-time applications in the palm oil industry. This study contributes to reducing the reliance on manual techniques, lowering operational costs, and increasing the overall efficiency of the oil palm industry.
 
Keywords—deep learning, You Only Look Once (YOLO)v8, object detection, oil palm fresh fruit bunch, computer vision


Copyright © 2026 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).