A YOLO-Based Framework for Automated Food Recognition and Nutrient Adequacy Estimation in the Free Nutritious Meal Program
Downloads
The Free Nutritious Meal (MBG) program in Indonesia may not consistently meet nutritional standards, providing an average of 377 of the targeted 531 calories per serving, with insufficient protein and fat. Limited nutritional information from food images makes independent meal assessment difficult. This study develops an image-based food detection system using You Only Look Once (YOLO) to estimate the nutritional adequacy of MBG meals based on Recommended Dietary Allowances (AKG). The study used Knowledge Discovery in Databases (KDD)- guided data management and Rapid Application Development (RAD)- guided system development. A dataset of 1.200 images across 51 food classes was evaluated using YOLO 8-YOLO 12, utilizing 5-fold cross-validation, followed by retraining and a 1.000 iteration bootstrap analysis on 240 test images. Average mAP50 scores were 0.8981, 0.898, 0.896, 0.894, and 0.888 for YOLO 8, YOLO 9, YOLO 11, YOLO 12, and YOLO 10. The Kruskal-Wallis test indicated significant differences among models (H = 489.946; p < 0.001), and YOLO 8 was selected because it had the highest bootstrap mean rank. Detected food classes were assigned reference serving weights rather than measured mass or volume, converted to nutrient values using the Indonesian Food Composition Table (TKPI), and compared with AKG by school level, age, and gender. Validation against nutritionist assessments across five nutrients produced a mean absolute percentage error of 40.31%, with energy and carbohydrate showing the closest agreement. A sensitivity analysis showed a 20 percent portion-weight error most strongly affected iron and calcium adequacy. Because nutrient values rely on reference assumptions rather than measured mass or volume, the outputs represent an estimate, not a definitive assessment of nutritional adequacy. YOLO 8 was the most suitable model and the highest mean rank assumption-based estimation approach for MBG nutritional screening, with direct mass or volume measurement recommended for future work.
[1] G. D. Dirawan and A. Sukriadi, “Beyond School Feeding : Makan Bergizi Gratis ( MBG ) as a Life-Course Nutrition and Human Capital Policy in Indonesia,” Pinisi J. Educ., vol. 6, no. 2, pp. 99–114, 2026, doi: 10.26858/c3jnxs65.
[2] R. Rimbawan, R. Nurdiani, P. H. Rachman, Y. Kawamata, and Y. Nozawa, “School Lunch Programs and Nutritional Education Improve Knowledge, Attitudes, and Practices and Reduce the Prevalence of Anemia: A Pre-Post Intervention Study in an Indonesian Islamic Boarding School,” Nutrients, vol. 15, no. 4, 2023, doi: 10.3390/nu15041055.
[3] Faramitha, Hendrayati, and Nadimin, “Analysis of Energy and Nutrient Adequacy in Two Menu Variants of the Free Nutritious Meal ( MBG ) Program for Adolescents in Makassar City,” Aceh Nutr. J., vol. 10, no. 4, pp. 1166–1174, 2025, doi: 10.30867/action.v10i4.3008.
[4] S. Kokare and P. Kandekar, “Food Detection and Nutrition Analysis by Image,” Int. J. Res. Appl. Sci. Eng. Technol., vol. 12, pp. 306–312, 2024, doi: 10.22214/ijraset.2024.64899.
[5] B. Gonzalez, G. Garcia, S. A. Velastin, H. GholamHosseini, L. Tejeda, and G. Farias, “Automated Food Weight and Content Estimation Using Computer Vision and AI Algorithms,” Sensors, vol. 24, no. 23, pp. 1–19, 2024, doi: 10.3390/s24237660.
[6] G. Chrintz-Gath, M. Daivadanam, L. Matta, and S. McKeever, “Image-Based Dietary Assessment Using The Swedish Plate Model: Evaluation of Deep Learning–Based You Only Look Once (YOLO) Models,” JMIR Form. Res., vol. 9, pp. 1–15, 2025, doi: 10.2196/70124.
[7] A. Sani et al., “Identification Food Nutrition and Weight Prediction Using Image Processing,” J. Appl. Electr. Eng., vol. 9, no. 1, pp. 28–36, 2025, doi: 10.30871/jaee.v9i1.9492.
[8] F. Romadhon et al., “Food Image Detection System and Calorie Content Estimation Using Yolo to Control Calorie Intake in The Body,” E3S Web Conf., vol. 465, pp. 1–7, 2023, doi: 10.1051/e3sconf/202346502057.
[9] G. C. Utami, C. Raras, A. Widiawati, and P. Subarkah, “Detection of Indonesian Food to Estimate Nutritional Information Using YOLOv5,” J. Inf. Commun. Technol., vol. 12, no. 2, pp. 158–165, 2023, doi: 10.34148/teknika.v12i2.636.
[10] A. Karabay, H. A. Varol, and M. Y. Chan, “Improved Food Image Recognition by Leveraging Deep Learning and Data-Driven Methods with an Application to Central Asian Food Scene,” Sci. Rep., vol. 15, no. 1, pp. 1–12, 2025, doi: 10.1038/s41598-025-95770-9.
[11] Y. Shi et al., “Calorie Detection in Dishes Based on Deep Learning and 3D Reconstruction,” Comput. Electron. Agric., vol. 229, pp. 1–12, 2025, doi: 10.1016/j.compag.2024.109832.
[12] P. Hidayatullah, N. Syakrani, M. R. Sholahuddin, T. Gelar, and R. Tubagus, “YOLOv8 to YOLO11: A Comprehensive Architecture In-Depth Comparative Review,” Rekayasa Sist. dan Teknol. Inf., vol. 10, no. 2, pp. 341–354, 2026, doi: 10.29207/resti.v10i2.6598.
[13] A. Sharma, V. Kumar, and L. Longchamps, “Comparative performance of YOLOv8, YOLOv9, YOLOv10, YOLOv11 and Faster R-CNN models for detection of multiple weed species,” Smart Agric. Technol., vol. 9, p. 100648, 2024, doi: 10.1016/j.atech.2024.100648.
[14] G. More, O. Patil, O. More, M. More, S. Suryavanshi, and M. Mali, “Comparison of Object Detection Algorithms CNN, YOLO and SSD,” Int. J. Sci. Res. Technol., vol. 1, no. 11, pp. 137–144, 2024, doi: 10.5281/zenodo.14186397.
[15] S. Patil, S. Patil, V. Kale, and M. Bonde, “Food Item Calorie Estimation Using YOLOv4 and Image Processing,” Int. J. Comput. Trends Technol., vol. 69, no. 5, pp. 69–76, 2021, doi: 10.14445/22312803/IJCTT-V69I5P110.
[16] M. Gerasimchuk and A. Uzhinskiy, “Food Recognition for Smart Restaurants and Self-Service Cafes,” Phys. Part. Nucl. Lett., vol. 21, no. 1, pp. 79–83, 2024, doi: 10.1134/S1547477124010059.
[17] R. Shankar and A. Yip, “Transforming Patient Feedback Into Actionable Insights Through Natural Language Processing: Knowledge Discovery and Action Research Study,” JMIR Form. Res., vol. 9, pp. 1–14, 2025, doi: 10.2196/69699.
[18] M. A. Fauzi, H. Tribiakto, A. Moniva, F. Amir, I. K. Ilyas, and E. Utami, “Systematic Literature Reviews on Rapid Application Development Information System,” Bull. Comput. Sci. Electr. Eng., vol. 4, no. 1, pp. 57–64, 2023, doi: 10.25008/bcsee.v4i1.1181.
[19] R. Sapkota and M. Karkee, “Ultralytics YOLO Evolution: An Overview of YOLO26, YOLO11, YOLOv8 and YOLOv5 Object Detectors for Computer Vision and Pattern Recognition,” pp. 1–16, 2026, doi: 10.48550/arXiv.2510.09653.
[20] K. Alomar, H. I. Aysel, and X. Cai, “Data Augmentation in Classification and Segmentation: A Survey and New Strategies,” J. Imaging, vol. 9, no. 2, p. 46, Feb. 2023, doi: 10.3390/jimaging9020046.
[21] T. M. Omoniyi et al., “The Effect of Data Augmentation on Performance of Custom and Pre-Trained CNN Models for Crack Detection,” Appl. Sci., vol. 15, no. 22, p. 12321, Nov. 2025, doi: 10.3390/app152212321.
[22] X. Du, Y. Sun, Y. Song, W. Chi, L. Dong, and X. Zhao, “Impact of Input Image Resolution on Deep Learning Performance for Side-Scan Sonar Classification: An Accuracy–Efficiency Analysis,” Remote Sens., vol. 17, no. 14, pp. 1–24, 2025, doi: 10.3390/rs17142431.
[23] A. Ichwani, R. I. Kesuma, A. Setiawan, I. E. Wicaksono, and R. Hanifah, “Preventing Data Leakage in Classification via Integrated Machine Learning Pipelines: Preprocessing, Feature Transformation, and Hyperparameter Tuning,” J. Tek. Inform., vol. 7, no. 1, pp. 391–410, 2026, doi: 10.52436/1.jutif.2026.7.1.5490.
[24] J. Terven, D. M. C. Esparza, and J. A. R. Gonzales, “A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NAS,” Mach. Learn. Knowl. Extr., vol. 5, no. 4, pp. 1680–1716, Nov. 2023, doi: 10.3390/make5040083.
[25] Z. Hu, W. Chen, D. Yang, Z. Wang, and P. Wang, “Enhancing Object Detection in Remote Sensing Images with Improved YOLOv8 Model,” Sci. Rep., vol. 15, pp. 1–14, 2025, doi: 10.1038/s41598-025-26536-6.
[26] Z. Zheng, P. Wang, W. Liu, J. Li, R. Ye, and D. Ren, “Distance-IoU loss: Faster and Better Learning For Bounding Box Regression,” Proc. AAAI Conf. Artif. Intell., vol. 34, no. 7, pp. 12993–13000, 2020, doi: 10.1609/aaai.v34i07.6999.
[27] S. M. A. H. Shah, A. Rizwan, G. Atteia, and M. Alabdulhafith, “CADFU for Dermatologists: A Novel Chronic Wounds & Ulcers Diagnosis System with DHuNeT (Dual-Phase Hyperactive UNet) and YOLOv8 Algorithm,” Healthc., vol. 11, no. 21, pp. 1–22, 2023, doi: 10.3390/healthcare11212840.
[28] X. Li et al., “Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection,” Adv. Neural Inf. Process. Syst., vol. 33, pp. 1–14, 2020, doi: 10.48550/arXiv.2006.04388.
[29] J. Wei, A. A. Arry, K. A. M. Rezali, M. Z. M. Yusoff, H. Ma, and K. Zhang, “A Review of YOLO Algorithm and Its Applications in Autonomous Driving Object Detection,” IEEE Access, 2025, doi: 10.1109/ACCESS.2025.3573376.
[30] J. Allgaier and R. Pryss, “Cross-Validation Visualized: A Narrative Guide to Advanced Methods,” Mach. Learn. Knowl. Extr., vol. 6, no. 2, pp. 1378–1388, 2024, doi: 10.3390/make6020065.
[31] S. F. Mokhtar, Z. Md Yusof, and H. Sapiri, “Confidence Intervals by Bootstrapping Approach: A Significance Review,” Malaysian J. Fundam. Appl. Sci., vol. 19, no. 1, pp. 30–42, Feb. 2023, doi: 10.11113/mjfas.v19n1.2660.
[32] N. K. Rajpoot, P. D. Singh, B. Pant, and M. Sharma, “An Intelligent Framework for Real-Time Heart Stroke Monitoring and Early Detection Using Machine Learning,” Cureus J. Comput. Sci., vol. 2, 2025, doi: 10.7759/s44389-025-04004-6.
[33] U. Ahmad, M. A. Rosyid, and Mardison, “Abnormal Shapes Identification of Gedong Mango Using Dimensionless Shape Factors in Image Processing,” Earth Environ. Sci., vol. 1038, 2022, doi: 10.1088/1755-1315/1038/1/012045.
[34] J. Terven, D. M. Cordova Esparza, J. A. R. González, A. Ramírez Pedraza, and E. A. Chávez Urbiola, “A Comprehensive Survey of Loss Functions and Metrics in Deep Learning,” Artif. Intell. Rev., vol. 58, no. 7, p. 195, Apr. 2025, doi: 10.1007/s10462-025-11198-7.
[35] M. Nasari, G. A. Tarigan, N. A. P. Masaling, S. Joddy, and K. A. Minor, “Indonesian Food Detection with YOLO and Calorie Estimation Using Lightweight LLMs,” IEEE Xplore, vol. 25, 2025, doi: 10.1109/ISRITI68345.2025.11393164.
[36] I. Hantoro, J. Wang, A. J. Löhr, F. G. A. J. Van Belleghem, B. Widianarko, and A. M. J. Ragas, “Assessing Age- Specific Variability in Microplastic Intake Through Seafood Consumption: A Case Study in Central Java, Indonesia,” J. Food Sci., vol. 91, no. 3, 2026, doi: 10.1111/1750-3841.70909.
[37] F. N. Nwobi and F. C. Akanno, “Power comparison of ANOVA and Kruskal–Wallis Tests When Error Assumptions Are Violated,” Adv. Methodol. Stat., vol. 18, no. 2, pp. 53–71, 2021, doi: 10.51936/ltgt2135.
[38] C. Sergio et al., “Beyond the Nutrition5k Project: Data Curation and Deep Learning Algorithms to Predict the Nutritional Composition of Dishes from Food Images,” Epidemiol. Biostat. Public Heal., vol. 20, no. 1, pp. 150–152, 2025, doi: 10.54103/2282-0930/29429.
[39] P. Ma, C. P. Lau, N. Yu, A. Li, and J. Sheng, “Application of deep learning for image-based Chinese market food nutrients estimation,” Food Chem., vol. 373, p. 130994, Mar. 2022, doi: 10.1016/j.foodchem.2021.130994.
[40] A. N. bin A. Faris, N. H. A. Razak, and M. M. Din, “Deep Learning for Meal Recognition and Calorie Estimation,” 5th Int. Conf. Inf. Technol. Secur., vol. 5, no. 1, pp. 357–362, 2024, doi: 10.32664/ic-itechs.v5i1.1679.
Copyright (c) 2026 Amelia Prachintya Putri Arifin, Wiyli Yustanti, Mega MIrasaputri Cahyanti (Author)
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-ShareAlikel 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).
