YOLOv11 for Classification of Strawberry Quality and Ripeness
Abstract
Strawberries hold significant economic value in Indonesia due to their high demand and nutritional benefits. Traditional harvesting methods, which rely on manual visual inspection, are often inefficient and prone to errors. Real-time multi-object detection presents a promising solution to enhance automation in harvesting, ripeness classification, and post-harvest processing. This study assesses the performance of four YOLOv11 variants—YOLOv11N, YOLOv11S, YOLOv11M, and YOLOv11L—in detecting strawberries across five quality and ripeness categories: Unripe, Half Ripe Grade B, Half Ripe Grade A, Fully Ripe Grade B, and Fully Ripe Grade A. A dataset originally consisting of 3,055 high-resolution strawberry images was expanded through data augmentation to 7,940 images. These were subsequently split into training (7,330 images), validation (305 images), and testing (305 images) sets. All models were trained under identical conditions utilizing the AdamW optimizer, cosine annealing learning rate scheduling, a batch size of 16, and an input resolution of 640×640 pixels. Performance was evaluated based on Precision, Recall, F1-Score, [email protected], [email protected], and inference time. The results indicate that YOLOv11N achieved the best overall performance, with a Precision of 0.869, Recall of 0.878, F1-Score of 0.87, [email protected] of 0.830, and the fastest inference time of 3.6 ms, rendering it suitable for real-time deployment. YOLOv11M provided a balanced trade-off between accuracy and speed, while YOLOv11S offered competitive accuracy with lower inference latency. YOLOv11L demonstrated strong detection capabilities but with the slowest inference time. These findings affirm the efficacy of YOLOv11-based models in facilitating scalable and intelligent systems for precision agriculture.
Keywords—strawberry, computer vision, deep learning, object detection, classification, YOLO.
References
F. Xiao, H. Wang, Y. Xu, dan R. Zhang, "Fruit Detection and Recognition Based on Deep Learning for Automatic Harvesting: An Overview and Review," Agronomy, vol. 13, no. 6, p. 1625, Jun. 2023.
H. Zhou, Y. Wang, J. Li, dan F. Chen, "Research on Kiwi Fruit Flower Recognition for Efficient Pollination Based on an Improved YOLOv5 Algorithm," Horticulturae, vol. 9, no. 3, p. 400, Mar. 2023.
R. Pathak dan H. Makwana, "Classification of Fruits Using Convolutional Neural Network and Transfer Learning Models," Journal of Management Information and Decision Sciences, vol. 24, Special Issue 3, pp. 1–12, 2021.
F. Wu dan J. Wang, "YOLO Deep Learning Algorithm for Object Detection in Agriculture: A Review," Journal of Agricultural Informatics, vol. 15, no. 2, pp. 34–45, 2024.
X. Li dan Y. Zhang, "Comparing YOLOv11 and YOLOv8 for Instance Segmentation in Orchard Environments," arXiv preprint, arXiv:2410.19869, 2024.
S. Azizah, M. Wahidin, M. Padang, L. Novamizanti, and S. Sa'idah, "Identifying the ripeness and quality level of strawberries based on YOLOv7-EfficientNet," in 2024 International Conference on Data Science and Its Applications (ICoDSA), Kuta, Bali, Indonesia, 2024, pp. 451–456, doi: 10.1109/ICoDSA62899.2024.10651988.
Y. Tian et al., "Apple Detection During Different Growth Stages in Orchards Using the Improved YOLO-V3 Model," Computers and Electronics in Agriculture, vol. 157, pp. 417–426, 2019.
I. Sa et al., "DeepFruits: A Fruit Detection System Using Deep Neural Networks," Sensors, vol. 16, no. 8, p. 1222, Aug. 2016.
L. Fu et al., "Faster R-CNN-Based Apple Detection in Dense-Foliage Fruiting-Wall Trees Using RGB and Depth Features," Biosystems Engineering, vol. 197, pp. 245–256, 2020.
M. Rahnemoonfar dan C. Sheppard, "Deep Count: Fruit Counting Based on Deep Simulated Learning," Sensors, vol. 17, no. 4, p. 905, Apr. 2017.
N. Häni, P. Roy, dan V. Isler, "A Comparative Study of Fruit Detection and Counting Methods for Yield Mapping in Apple Orchards," Journal of Field Robotics, vol. 37, no. 2, pp. 263–282, 2020.
A. Koirala, K. B. Walsh, Z. Wang, dan C. McCarthy, "Deep Learning – Method Overview and Review of Use for Fruit Detection and Yield Estimation," Computers and Electronics in Agriculture, vol. 162, pp. 219–234, 2019.
M. Stein, S. Bargoti, dan J. Underwood, "Image Based Mango Fruit Detection, Localisation and Yield Estimation Using Multiple View Geometry," Sensors, vol. 16, no. 11, p. 1915, Nov. 2016.
S. Chen, J. Yang, dan L. Deng, "An Improved YOLOv5 Model Based on Attention Mechanism for Detection of Small-Size Fruits in Complex Backgrounds," Computers and Electronics in Agriculture, vol. 181, p. 105951, 2021.
H. Kang dan C. Chen, "Apple Detection in Complex Scene Using the Improved YOLOv4 Model," Agronomy, vol. 11, no. 3, p. 476, Mar. 2021.
F. Akhyar, L. Novamizanti, T. Putra, E. N. Furqon, M.-C. Chang, and C.-Y. Lin, “Lightning YOLOv4 for a Surface Defect Detection System for Sawn Lumber,” in 2022 IEEE Conference on Multimedia Information Processing and Retrieval (MIPR), 2022, pp. 168–173, doi: 10.1109/MIPR54900.2022.00039.
K. Aziz, M. D. Maulana, R. F. Adawiyah, R. F. Firdaus, L. Novamizanti, and F. Ramdhon, “Comparative analysis of YOLOv8 models in skipjack fish quality assessment system,” in Proc. 2023 3rd Int. Conf. Intell. Cybern. Technol. Appl. (ICICyTA), 2023, pp. 237–242.
F. Akhyar, L. Novamizanti, K. Usman, G. M. Aditya, F. N. Hakim, M. Z. Ilman, F. Ramdhon, and C.-Y. Lin, “A comparative analysis of the YOLO models for intelligent lobster surveillance camera,” in Proc. 2023 Asia Pacific Signal Inf. Process. Assoc. Annu. Summit Conf. (APSIPA ASC), 2023, pp. 2131–2136.
Y. Wu, H. Li, and Y. Gao, "Lightweight Attention-Enhanced YOLO Model for Pomegranate Detection in Complex Environments," Scientific Reports, vol. 14, no. 1, p. 3129, 2024.
R. Padilla, W. L. Passos, T. L. B. Dias, S. L. Netto, and E. A. B. da Silva, "A Comparative Analysis of Object Detection Metrics with a Companion Open-Source Toolkit," Electronics, vol. 10, no. 3, p. 279, 2021.
L. Alzubaidi et al., “A survey on deep learning tools dealing with data scarcity: definitions, challenges, solutions, tips, and applications,” *Journal of Big Data*, vol. 10, no. 1, p. 46, 2023. doi:10.1186/s40537-023-00727-2.
