Implementation of YOLOv11 for Detection and Identification of Strawberry Ripeness Stages
DOI:
https://doi.org/10.30871/jaic.v10i2.12283Keywords:
YOLOv11, Object Detection, Strawberry Ripeness Stages, Computer Vision, Post-Harvest SortingAbstract
This study presents the implementation and evaluation of YOLOv11m, the latest architecture in the YOLO (You Only Look Once) object detection family, for automated multi-stage strawberry ripeness detection. The model was trained on a publicly available Strawberry-DS dataset from Mendeley Data comprising 247 annotated images across six ripeness classes: Green, White, Early-Turning, Turning, Late-Turning, and Red. The dataset was split using stratified sampling into training (70%, 172 images), validation (20%, 49 images), and test (10%, 26 images) subsets. Images were resized to 224×224 pixels and augmented using mosaic, horizontal flipping, HSV adjustment, and random scaling to improve model robustness. Training was performed for 100 epochs using SGD with cosine learning rate scheduling and early stopping. The YOLOv11m model consists of 125 fused layers, 20,034,658 parameters, and 67.7 GFLOPs. Evaluation on the validation set yielded mean precision of 0.748, recall of 0.590, [email protected] of 0.654, and [email protected]:0.95 of 0.460. The Red (fully ripe) class achieved the highest performance ([email protected] = 0.889), while transitional classes showed lower scores due to class imbalance and visual similarity. The model achieved an inference speed of 50.1 ms/image (~19 FPS) on a CPU, demonstrating real-time feasibility for industrial deployment. Unlike previous binary or three-class approaches, this study provides fine-grained six-stage ripeness detection with simultaneous object localization, offering a more granular and practically applicable framework for automated post-harvest sorting of strawberries.
Downloads
References
[1] F. Giampieri, S. Tulipani, J. M. Alvarez-Suarez, J. L. Quiles, B. Mezzetti, and M. Battino, "The strawberry: Composition, nutritional quality, and impact on human health," Nutrition, vol. 28, no. 1, pp. 9-19, Jan. 2012.
[2] J. K. Brecht, M. A. Ritenour, N. F. Haard, and G. W. Chism, "Postharvest physiology of vegetables," in Handbook of Vegetable Science and Technology, D. K. Salunkhe and S. S. Kadam, Eds. New York, NY: Marcel Dekker, 1998, pp. 97–158.
[3] S. J. Kays, Postharvest Physiology of Perishable Plant Products. New York, NY: Van Nostrand Reinhold, 1991.
[4] K. Tanaka and Y. Sato, "Machine vision applications in precision agriculture: A review," Agricultural Systems, vol. 189, pp. 103–121, 2021.
[5] Y. LeCun, Y. Bengio, and G. Hinton, "Deep learning," Nature, vol. 521, no. 7553, pp. 436–444, May 2015.
[6] X. Wang and D. Zhang, "Convolutional neural networks for fruit maturity classification: Recent advances and applications," Computers and Electronics in Agriculture, vol. 175, p. 105547, Aug. 2020.
[7] J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, "You only look once: Unified, real-time object detection," in Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, Jun. 2016, pp. 779–788.
[8] G. Jocher, A. Chaurasia, and J. Qiu, "Ultralytics YOLO11," GitHub repository, 2024. [Online]. Available: https://github.com/ultralytics/ultralytics
[9] R. E. Saragih and A. W. R. Emanuel, "Banana ripeness classification based on deep learning using convolutional neural network," in 2021 3rd East Indonesia Conference on Computer and Information Technology (EIConCIT), Surabaya, Indonesia, Apr. 2021, pp. 85–89.
[10] M. Afonso, H. Fonteijn, F. S. Fiorentin, D. Lensink, M. Mooij, N. Faber, G. Polder, and R. Wehrens, "Tomato fruit detection and counting in greenhouses using deep learning," Frontiers in Plant Science, vol. 11, p. 571299, Oct. 2020.
[11] Z. Tao, K. Li, Y. Rao, W. Li, and J. Zhu, "Strawberry maturity recognition based on improved YOLOv5," Agronomy, vol. 14, no. 3, p. 460, Feb. 2024.
[12] C. Wang, H. Wang, Q. Han, Z. Zhang, D. Kong, and X. Zou, "Strawberry detection and ripeness classification using YOLOv8+ model and image processing method," Agriculture, vol. 14, no. 5, p. 751, May 2024.
[13] N. El-Bendary and E. Elhariri, "Strawberry-DS: An annotated benchmark strawberry ripeness dataset," Mendeley Data, v.1, 2022.
[14] A. Bochkovskiy, C.-Y. Wang, and H.-Y. M. Liao, "YOLOv4: Optimal speed and accuracy of object detection," arXiv preprint arXiv:2004.10934, 2020.
[15] R. Padilla, S. L. Netto, and E. A. B. da Silva, "A survey on performance metrics for object-detection algorithms," in Proc. Int. Conf. Systems, Signals and Image Processing (IWSSIP), 2020, pp. 237–242.
[16] S. Ren, K. He, R. Girshick, and J. Sun, "Faster R-CNN: Towards real-time object detection with region proposal networks," in Advances in Neural Information Processing Systems (NIPS), vol. 28, 2015, pp. 91–99.
[17] P. Behera, A. Behera, and A. K. Sethy, "Maturity status classification of papaya fruits based on machine learning and transfer learning approach," Information Processing in Agriculture, vol. 8, no. 2, pp. 244–250, Jun. 2021.
[18] Y. Han, C. Wang, H. Luo, H. Wang, Z. Chen, Y. Xia, and L. Yun, "LRDS-YOLO enhances small object detection in UAV aerial images with a lightweight and efficient design," Scientific Reports, vol. 15, art. no. 22627, 2025.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Nilla Mery Handayani, Yufis Azhar
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).
