Comparative Performance Analysis of Models from YOLOv6 to YOLOv11 on Food Waste Datasets

Abstract

Food waste has emerged as a significant global issue, both due to the economic losses it causes and its threat to the sustainable use of natural resources. In this study, different versions of the YOLO (You Only Look Once) family, ranging from YOLOv6 to YOLOv11, were compared to enable the automatic detection and classification of food waste. Using two different datasets, performance metrics such as inference speed, accuracy rates (precision, recall), and mean average precision (mAP50, mAP50-95) were analysed for each model. The results demonstrated that the model performance trends varied based on the characteristics of the dataset. In the first dataset, YOLOv9 offered relatively higher accuracy and broader coverage, whereas in the second dataset, YOLOv8 provided a more balanced precision-recall profile. Furthermore, inference times revealed that some models, despite being the latest versions, were not the fastest or most accurate. The performances of the models were also evaluated using two test images. For the first image, YOLOv6 produced higher accuracy than other models but made erroneous or excessive predictions for certain classes. For the second, YOLOv10 and YOLOv11 correctly detected all classes, while earlier models missed or misclassified some. These findings demonstrate the performance limitations of the models when dealing with images containing complex backgrounds and diverse food types. Moreover, they emphasise the importance of considering dataset characteristics, hardware constraints, and application objectives when selecting models. Such considerations can improve the efficiency and sustainability of the intelligent systems developed to detect food waste.

Keywords

• Image Processing
• Object Detection
• YOLO
• Food Waste

References

1. Agbehadji, I. E., Abayomi, A., Bui, K. H. N., Millham, R. C., & Freeman, E. (2022). Nature inspired search method and custom waste object detection and classification model for smart waste bin. Sensors, 22(16), 6176. https://doi.org/10.3390/s22166176 google scholar
2. Aschemann-Witzel, J., De Hooge, I., Amani, P., Bech-Larsen, T., & Oostindjer, M. (2015). Consumer-related food waste: Causes and potential for action. Sustainability, 7(6), 6457–6477. https://doi.org/10.3390/su7066457 google scholar
3. Bisong, E. (2019). Google colaboratory. In Building machine learning and deep learning models on Google Cloud Platform: A comprehensive guide for beginners (pp. 59–64). Apress. https://doi.org/10.1007/978-1-4842-4470-8_7 google scholar
4. Food and Agriculture Organization of the United Nations. (2011). Global food losses and food waste – Extent, causes and prevention [Report]. Food and Agriculture Organization of the United Nations. google scholar
5. Garcia-Garcia, G., Woolley, E., Rahimifard, S., Colwill, J., White, R., & Needham, L. (2017). A methodology for sustainable management of food waste. Waste and Biomass Valorization, 8(6), 2209–2227. https://doi.org/10.1007/s12649-016-9720-0 google scholar
6. Jagtap, S., Bhatt, C., Thik, J., & Rahimifard, S. (2019). Monitoring potato waste in food manufacturing using image processing and internet of things approach. Sustainability, 11(11), 3173. https://doi.org/10.3390/su11113173 google scholar
7. Jahanbakhshi, A., Momeny, M., Mahmoudi, M., & Radeva, P. (2021). Waste management using an automatic sorting system for carrot fruit based on image processing technique and improved deep neural networks. Energy Reports, 7, 5248–5256. https://doi.org/10.1016/j.egyr.2021.08.114 google scholar
8. Jocher, G., Chaurasia, A., & Qiu, J. (2023). Ultralytics YOLOv8 [Computer software]. GitHub. https://github.com/ultralytics/ultralytics google scholar

9. Jocher, G., & Qiu, J. (2024). Ultralytics YOLOv11 [Computer software]. GitHub. https://github.com/ultralytics/ultralytics google scholar
10. leftover foods. (2024, May). Food dataset [Data set]. Universe.Roboflow. Retrieved January 29, 2025, from https://universe.roboflow.com/leftover-foods/food-vxkxm google scholar
11. Li, C., Li, L., Geng, Y., Jiang, H., Cheng, M., Zhang, B., & Chu, X. (2023). YOLOv6 v3.0: A full-scale reloading. arXiv preprint. https://doi.org/10.48550/arXiv.2301.05586 google scholar
12. Li, Y., Zhang, C., Xu, H., Yang, Y., Lu, H., & Deng, L. (2025). Strategies for automated identification of food waste in university cafeterias: A machine vision recognition approach. Applied Sciences, 15(9), 5036. https://doi.org/10.3390/app15095036 google scholar
13. Lubura, J., Pezo, L., Sandu, M. A., Voronova, V., Donsì, F., Šic Žlabur, J., & Voća, N. (2022). Food recognition and food waste estimation using convolutional neural network. Electronics, 11(22), 3746. https://doi.org/10.3390/electronics11223746 google scholar
14. Mazloumian, A., Rosenthal, M., & Gelke, H. (2020). Deep learning for classifying food waste. arXiv preprint. https://doi.org/10.48550/arXiv.2002.03786 google scholar
15. Morton, L. W., Bitto, E. A., Oakland, M. J., & Sand, M. (2008). Accessing food resources: Rural and urban patterns of giving and getting food. Agriculture and Human Values, 25(1), 107–119. https://doi.org/10.1007/s10460-007-9095-8 google scholar
16. Mustapha, A. A., Saruchi, S. A., Supriyono, H., & Solihin, M. I. (2025). A hybrid deep learning model for waste detection and classification utilizing YOLOv8 and CNN. Engineering Proceedings, 84(1), 82. https://doi.org/10.3390/engproc2023084082 google scholar
17. Parfitt, J., Barthel, M., & Macnaughton, S. (2010). Parfitt, J., Barthel, M., & Macnaughton, S. (2010). Food waste within food supply chains: quantification and potential for change to 2050. Philosophical Transactions of the Royal Society B: Biological Sciences, 365(1554), 3065–3081. https://doi.org/10.1098/rstb.2010.0126 google scholar
18. Paritosh, K., Kushwaha, S. K., Yadav, M., Pareek, N., Chawade, A., & Vivekanand, V. (2017). Food waste to energy: An overview of sustainable approaches for food waste management and nutrient recycling. BioMed Research International, 2017, 2370927. https://doi.org/10.1155/2017/2370927 google scholar
19. Rawat, W., & Wang, Z. (2017). Deep convolutional neural networks for image classification: A comprehensive review. Neural Computation, 29(9), 2352–2449. https://doi.org/10.1162/neco_a_00990 google scholar
20. Said, Z., Sharma, P., Nhuong, Q. T. B., Bora, B. J., Lichtfouse, E., Khalid, H. M., & Hoang, A. T. (2023). Intelligent approaches for sustainable management and valorisation of food waste. Bioresource Technology, 377, 128952. https://doi.org/10.1016/j.biortech.2023.128952 google scholar
21. Scherhaufer, S., Moates, G., Hartikainen, H., Waldron, K., & Obersteiner, G. (2018). Environmental impacts of food waste in Europe. Waste Management, 77, 98–113. https://doi.org/10.1016/j.wasman.2018.04.038 google scholar
22. Stancu, V., Haugaard, P., & Lähteenmäki, L. (2016). Determinants of consumer food waste behaviour: Two routes to food waste. Appetite, 96, 7–17. https://doi.org/10.1016/j.appet.2015.08.025 google scholar
23. trashDetect. (2024, October). Fall2021 dataset [Data set]. Universe.Roboflow. Retrieved January 29, 2025, from https://universe.roboflow.com/trashdetect-hxkvr/fall2021-luamm google scholar
24. Tzutalin. (2015). LabelImg [Computer software]. GitHub. https://github.com/tzutalin/labelImg google scholar
25. United Nations Environment Programme. (2024). Food Waste Index Report 2024 [Report]. United Nations Environment Programme. google scholar
26. Ultralytics. (2025). YOLO Models [Online documentation]. Ultralytics Documentation. Retrieved May 31, 2025, from https://docs.ultralytics.com/models/ google scholar
27. Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., … & Polosukhin, I. (2017). Attention is all you need. In Advances in Neural Information Processing Systems (Vol. 30). Curran Associates. https://doi.org/10.48550/arXiv.1706.03762 google scholar
28. Ver Ploeg, M., Breneman, V., Farrigan, T., Hamrick, K., Hopkins, D., Kaufman, P., … & Tuckermanty, E. (2009). Access to affordable and nutritious food: Measuring and understanding food deserts and their consequences: Report to Congress [Government Report]. USDA. Retrieved from https://www.ers.usda.gov/publications/pub-details/?pubid=42729 google scholar
29. Wang, A., Chen, H., Liu, L., Chen, K., Lin, Z., & Han, J. (2024). YOLOv10: Real-time end-to-end object detection. In Advances in Neural Information Processing Systems (Vol. 37, pp. 107984–108011). Curran Associates. google scholar
30. Wang, C.-Y., Bochkovskiy, A., & Liao, H.-Y. M. (2023). YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 7464–7475). IEEE. https://doi.org/10.1109/CVPR52688.2023.00732 google scholar
31. Wang, C.-Y., Yeh, I.-H., & Liao, H.-Y. M. (2024). YOLOv9: Learning what you want to learn using programmable gradient information. In European Conference on Computer Vision (pp. 1–21). Springer Nature Switzerland. https://doi.org/10.1007/978-3-031-50064-6_1 google scholar