Abstract

Accurate detection of vegetables from images is an essential task in precision agriculture, automated food supply chains and smart retail systems. Even with a little labeled data, recent developments in deep learning, especially pretrained object detection models, have greatly enhanced performance on visual recognition tasks.. However, the relative effectiveness of modern pretrained object detection architectures on agricultural datasets remains underexplored. In this study, we present a comprehensive comparative evaluation of multiple state-of-the-art pretrained object detection models on a publicly available vegetable object detection dataset from Bangladesh. The evaluated models include RF-DETR (Large), YOLOv11 variants, Roboflow 3.0 Object Detection models and YOLOv12 variants with different capacity configurations (Fast, Accurate and Extra Large). Standard metrics like recall, precision and mAP@50 on a predetermined test set are used to evaluate performance. Experimental results demonstrate that YOLOv12 (Extra Large) significantly outperforms other models, achieving an mAP@50 of 79.0%, precision of 81.8% and recall of 80.7%. When implementing pretrained detectors in agricultural computer vision applications, the results emphasize the significance of model architecture and scale.

References

• Alamsyah, A.N., Prasetyo, N.A., Wibowo, F.M., Amrulloh, A., Sari, P.K. (2023). An implementation of YOLOv5 and flutter framework for fruit and vegetable object detection. In: The Proceeding Book of 2023 IEEE International Conference on Communication, Networks and Satellite (COMNETSAT), Malang, Indonesia, 259-264, doi: 10.1109/COMNETSAT59769.2023.10420564
• Atasoy, H., & Kutlu, Y. (2022). Parameter Selection in Elliptical Fourier Series for Leaf Classification. Dokuz Eylül Üniversitesi Mühendislik Fakültesi Fen ve Mühendislik Dergisi, 24(71), 375-381. https://doi.org/10.21205/deufmd.2022247104
• Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S. (2020). End-to-end object detection with transformers. In: The Proceeding Book of 16th European Conference on Computer Vision (ECCV 2020), Glasgow, UK, 213-229, doi: 10.1007/978-3-030-58452-8_13
• Camgözlü, Y., Kutlu, Y. (2023). Leaf image classification based on pre-trained convolutional neural network models. Natural and Engineering Sciences, 8(3), 214-232.
• Camgözlü, Y., Kutlu, Y. (2020). Analysis of Filter Size Effect in Deep Learning. Journal of Artificial Intelligence with Applications, 1(1), 20-29, doi : 10.5281/zenodo.4540543
• Jahan, S., Alam, B.S., Manzur, I., Rahman, T., Hasan, M., Gani, R., Hossain, M., Shams, K., Rashid, M.R.A. (2025). Smartphone-based multi-criteria vegetable object detection dataset from Bangladesh. Data in Brief, 112281, doi: 10.1016/j.dib.2025.112281
• Jocher, G., Chaurasia, A., Qiu, J. (2023). Ultralytics, YOLOv8. https://docs.ultralytics.com/models/YOLOv8/, version (01/2026).
• Khanam, R., Hussain, M. (2024). YOLOv11: An overview of the key architectural enhancements. arXiv preprint, arXiv:2410.17725, doi: 10.48550/arXiv.2410.17725
• Khanna, S., Chattopadhyay, C., Kundu, S. (2024). Enhancing fruit and vegetable detection in unconstrained environment with a novel dataset. Scientia Horticulturae, 338, 113580, doi: 10.1016/j.scienta.2024.113580
• Kurniawan, H., Arief, M. A. A., Lohumi, S., Kim, M. S., Baek, I., Cho, B.-K. (2024). Dual imaging technique for a real-time inspection system of foreign object detection in fresh-cut vegetables. Current Research in Food Science, 9, 100802, doi: 10.1016/j.crfs.2024.100802
• Li, J., Qiao, Y., Liu, S., Zhang, J., Yang, Z., Wang, M. (2022). An improved YOLOv5-based vegetable disease detection method. Computers and Electronics in Agriculture, 202, 107345, doi: 10.1016/j.compag.2022.107345
• Lin, T. Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Dollar, P., Zitnick, C. L. (2014). Microsoft coco: Common objects in context. In: The Proceeding Book of 13th European Conference on Computer Vision, Zurich, Switzerland, 740-755, doi: 10.1007/978-3-319-10602-1_48
• Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.Y., Berg, A.C. (2016). Ssd: Single shot multibox detector. In: The Proceeding Book of 14th European Conference on Computer Vision, Amsterdam, The Netherlands, 21-37, doi: 10.1007/978-3-319-46448-0_2
• Lohumi, S., Cho, B.-K., Hong, S. (2021). LCTF-based multispectral fluorescence imaging: System development and potential for real-time foreign object detection in fresh-cut vegetable processing. Computers and Electronics in Agriculture, 180, 105912, doi: 10.1016/j.compag.2020.105912
• Redmon, J., Divvala, S., Girshick, R., Farhadi, A. (2016). You only look once: Unified, real-time object detection. In: The Proceeding Book of 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, USA, 779-788.
• Ren, S., He, K., Girshick, R., Sun, J. (2015). Faster R-CNN: Towards real-time object detection with region proposal networks. Advances in Neural Information Processing Systems, 28, 1-9.
• Sakai, Y., Oda, T., Ikeda, M., Barolli, L. (2016). A vegetable category recognition system using deep neural network. In: The Proceeding Book of 10th International Conference on Innovative Mobile and Internet Services in Ubiquitous Computing (IMIS), Fukuoka, Japan, 189-192, doi: 10.1109/IMIS.2016.84
• Tapia-Mendez, E., Hernandez-Sandoval, M., Salazar-Colores, S., Cruz-Albarran, I.A., Tovar-Arriaga, S., Morales-Hernandez, L.A. (2025). A novel deep learning approach for precision agriculture: quality detection in fruits and vegetables using object detection models. Agronomy, 15(6), 1307, doi: 10.3390/agronomy15061307
• Wang, X., Liu, J. (2024). Vegetable disease detection using an improved YOLOv8 algorithm in the greenhouse plant environment. Scientific Reports, 14, 4261, doi: 10.1038/s41598-024-54540-9
• Zeng, G. (2017). Fruit and vegetables classification system using image saliency and convolutional neural network. In: The Proceeding Book of 2017 IEEE 3rd Information Technology and Mechatronics Engineering Conference (ITOEC), Chongqing, China, 613-617, doi: 10.1109/ITOEC.2017.8122370
• Zhu, C., Jia, J., Arslan, T. (2026). FVOR-YOLO: A real-time model for fruits and vegetables detection in complex supermarket self-checkout environments. IEEE Internet of Things Journal. doi: 10.1109/JIOT.2025.3643299