COMPARATIVE EVALUATION OF YOLOV5–YOLOV11 MODELS FOR DETECTING NUTRIENT DEFICIENCY IN CHILI SEEDLINGS
DOI:
https://doi.org/10.33480/jitk.v11i4.8263Keywords:
Chili Leaves, Comparison, Nutrient Detection, YOLOAbstract
Nutrient deficiencies during the seedling stage of chili plants can reduce crop productivity, while conventional identification methods remain subjective and costly. This study compares YOLOv5 to YOLOv11 object detection models for detecting nutrient deficiency symptoms in Bonita chili seedling leaves, including complete nutrition, nitrogen deficiency, phosphorus deficiency, potassium deficiency, and NPK deficiency. The final dataset comprised 4,173 images derived from 1,739 original annotated leaf images through controlled dataset preparation, including split-before-augmentation, laboratory validation of nutrient conditions, and expert-reviewed labeling. All YOLO models were trained and evaluated using the same dataset partition and comparable experimental settings. Performance was assessed using mAP@0.5, computational complexity (FLOPs), inference speed, and model size. The results show that all evaluated models achieved high detection performance, with differences mainly appearing in computational efficiency and the balance between accuracy and speed. YOLOv10s and YOLOv11s obtained the highest mAP@0.5 in this experiment, whereas YOLOv8s showed a competitive balance between accuracy, inference speed, and model compactness. These findings indicate that recent YOLO developments are promising for fine-grained nutrient deficiency detection in computer vision–based precision agriculture.
Downloads
References
[1] M. T. Sundari, Darsono, J. Sutrisno, and E. Antriyandarti, “Analysis of chili farming in Indonesia,” IOP Conf. Ser. Earth Environ. Sci., vol. 905, no. 1, 2021, doi: 10.1088/1755-1315/905/1/012046.
[2] C. M. Badgujar, A. Poulose, and H. Gan, “Agricultural object detection with You Only Look Once (YOLO) Algorithm: A bibliometric and systematic literature review,” Comput. Electron. Agric., vol. 223, pp. 1–30, 2024, doi: 10.1016/j.compag.2024.109090.
[3] Nice Anjelin Gulo, Ayu Indah Purnama Mendrofa, Berliana Vivi Lestari Lase, Cynthia Florentina Mendrofa, Iman Viktor Telaumbanua, and Irwan Saham Laia, “Kurangnya Unsur Hara pada Tanaman Cabai Merah serta Pemeliharaannya,” Tumbuh. Publ. Ilmu Sosiol. Pertan. Dan Ilmu Kehutan., vol. 1, no. 3, pp. 13–20, 2024, doi: 10.62951/tumbuhan.v1i3.112.
[4] J. Permatasari, A. U. Edmund, E. Sunardi, B. M. Laili, and M. S. Putri, “Evaluasi Kinerja YOLOv11 pada Deteksi Penyakit Tanaman Cabai Studi Komparatif dengan YOLOv8, YOLOv5, dan SSD,” J. Teknol., vol. Vol. 25, N, 2025, [Online]. Available: https://e-jurnal.pnl.ac.id/teknologi/article/view/8400
[5] S. S. A. Begum and H. Syed, “GSAtt-CMNetV3: Pepper Leaf Disease Classification Using Osprey Optimization,” IEEE Access, vol. 12, no. January, pp. 32493–32506, 2024, doi: 10.1109/ACCESS.2024.3358833.
[6] D. T. Nguyen, T. D. Bui, T. M. Ngo, and U. Q. Ngo, “Improving YOLO-Based Plant Disease Detection Using αSILU: A Novel Activation Function for Smart Agriculture,” AgriEngineering, vol. 7, no. 9, pp. 1–25, 2025, doi: 10.3390/agriengineering7090271.
[7] R. Kaur et al., “YOLO-LeafNet: a robust deep learning framework for multispecies plant disease detection with data augmentation,” Sci. Rep., vol. 15, no. 1, pp. 1–23, 2025, doi: 10.1038/s41598-025-14021-z.
[8] M. Shoaib et al., “A deep learning-based model for plant lesion segmentation, subtype identification, and survival probability estimation,” 2022, frontiersin.org. doi: 10.3389/fpls.2022.1095547.
[9] M. Al-husaini, A. R. Raharja, V. Hafizh, C. Putra, and H. Hen, “Journal of Computer Networks , Architecture and High Performance Computing Enhanced Plant Disease Detection Using Computer Vision YOLOv11 : Pre- Trained Neural Network Model Application Journal of Computer Networks , Architecture and High Performance Comp,” vol. 7, no. 1, pp. 82–95, 2025, doi: 10.30871/jaic.v9i3.9213.
[10] J. Sikati and J. C. Nouaze, “YOLO-NPK: A Lightweight Deep Network for Lettuce Nutrient Deficiency Classification Based on Improved YOLOv8 Nano †,” 2023, mdpi.com. doi: 10.3390/ecsa-10-16256.
[11] F. Aldi, I. Nozomi, M. Hafizh, and T. Novita, “Comparative Analysis of YOLOv11 with Previous YOLO in the Detection of Human Bone Fractures,” vol. 7, no. 3, pp. 777–790, 2025, doi: 10.47709/cnahpc.v7i3.6051.
[12] M. L. Ali, “The YOLO Framework : A Comprehensive Review of Evolution , Applications , and Benchmarks in Object Detection,” Computers, vol. 13, no. 12, 2024, doi: 10.3390/computers13120336.
[13] R. Sapkota and M. Karkee, “Comparing YOLOv11 and YOLOv8 for instance segmentation of occluded and non-occluded immature green fruits in complex orchard environment,” arXiv preprint arXiv:2410.19869, 2025. doi: 10.48550/arXiv.2410.19869.
[14] J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, “You only look once: Unified, real-time object detection,” in Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2016, pp. 779–788. doi: 10.1109/CVPR.2016.91.
[15] U. Sirisha, S. P. Praveen, P. N. Srinivasu, P. Barsocchi, and A. K. Bhoi, “Statistical Analysis of Design Aspects of Various YOLO-Based Deep Learning Models for Object Detection,” Int. J. Comput. Intell. Syst., vol. 16, no. 1, pp. 1–18, 2023, doi: 10.1007/s44196-023-00302-w.
[16] J. Terven, D. M. Córdova-Esparza, and J. A. Romero-González, “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, 2023, doi: 10.3390/make5040083.
[17] M. Fathurrahman, A. Nugroho, A. Zein, and A. Wafi, “COMPARATIVE STUDY OF YOLO VERSIONS FOR DETECTING VACANT CAR PARKING SPACES,” vol. 10, no. 4, pp. 833–848, 2025, doi: 10.33480/jitk.v10i4.6236.
[18] M. Hou, W. Hao, Y. Dong, and Y. Ji, “A detection method for the ridge beast based on improved YOLOv3 algorithm,” Herit. Sci., pp. 1–13, 2023, doi: 10.1186/s40494-023-00995-4.
[19] Z. Zou, K. Chen, Z. Shi, Y. Guo, and J. Ye, “Object Detection in 20 Years: A Survey,” Proc. IEEE, vol. 111, no. 3, pp. 257–276, 2023, doi: 10.1109/JPROC.2023.3238524.
[20] M. A. R. Alif and M. Hussain, “YOLOv1 to YOLOv10: A comprehensive review of YOLO variants and their application in the agricultural domain,” arXiv preprint arXiv:2406.10139, 2024. doi: 10.48550/arXiv.2406.10139.
[21] R. Khanam and M. Hussain, “What is YOLOv5: A deep look into the internal features of the popular object detector,” arXiv preprint arXiv:2407.20892, 2024. doi: 10.48550/arXiv.2407.20892.
[22] Y. Lyu, “A Review of YOLO-Based Target Detection Methods,” vol. 0, pp. 59–66, 2024, doi: 10.54254/2755-2721/80/2024CH0060.
[23] J. E. Gallagher and E. J. Oughton, “Surveying You Only Look Once ( Yolo ) Multispectral Object Detection Advancements , Applications And Challenges,” IEEE Access, vol. PP, p. 1, 2025, doi: 10.1109/ACCESS.2025.3526458.
[24] M. Yang, X. Tong, and H. Chen, “Detection of Small Lesions on Grape Leaves Based on Improved YOLOv7,” Electronics, vol. 13. no 2, 2024.
[25] M. Yaseen, “What is YOLOv9: An In-Depth Exploration of the Internal Features of the Next-Generation Object Detector,” arXiv preprint arXiv:2409.07813, 2024. doi: 10.48550/arXiv.2409.07813.
[26] X. Wang, C. Zhang, Z. Qiang, C. Liu, X. Wei, and F. Cheng, “A Coffee Plant Counting Method Based on Dual-Channel NMS and YOLOv9 Leveraging UAV Multispectral Imaging,” Remote Sensing, vol. 16, no. 20, p. 3810, 2024. doi: 10.3390/rs16203810.
[27] Y. Wang, Q. Rong, and C. Hu, “Ripe Tomato Detection Algorithm Based on Improved YOLOv9,” Appl. Sci., vol. 14, no. 9, p. 3921, 2024, doi: 10.3390/app14093921.
[28] G. Jocher, “Ultralytics YOLO Docs.” [Online]. Available: https://docs.ultralytics.com/models/. [Accessed: May 22, 2026].
[29] A. S. Geetha, M. Al, R. Alif, M. Hussain, and P. Allen, “Comparative Analysis of YOLOv8 and YOLOv10 in Vehicle Detection : Performance Metrics and Model Efficacy,” pp. 1364–1382, 2024, doi: 10.3390/vehicles6030065.
[30] E. Nhancements, “YOLOV11 AN OVERVIEW OF THE KEY ARCHITECTURAL ENHANCEMENTS,” vol. 2024, pp. 1–9, 2024.
[31] L. He, Y. Zhou, and L. Liu, “Research and Application of YOLOv11-Based Object Segmentation in Intelligent Recognition at Construction Sites,” 2024.
[32] C. V Jul, C. Science, and H. Hd, “YOLOV5, YOLOV8 AND YOLOV10: THE GO - TO DETECTORS FOR REAL - TIME VISION,” pp. 1–12, 2024.
[33] D. C. Rodríguez-Lira, D. M. Córdova-Esparza, J. M. Álvarez-Alvarado, J. A. Romero-González, J. Terven, and J. Rodríguez-Reséndiz, “Comparative Analysis of YOLO Models for Bean Leaf Disease Detection in Natural Environments,” AgriEngineering, vol. 6, no. 4, pp. 4585–4603, 2024, doi: 10.3390/agriengineering6040262.
[34] N. Chitraningrum et al., “Comparison Study of Corn Leaf Disease Detection based on Deep Learning YOLO-v5 and YOLO-v8,” vol. 56, no. 1, pp. 61–70, 2024, doi: 10.5614/j.eng.technol.sci.2024.56.1.5.
[35] Kaur, J., Singh, W. "Tools, techniques, datasets and application areas for object detection in an image: a review." Multimed Tools Appl, vol. 81, pp. 38297–38351, 2022. https://doi.org/10.1007/s11042-022-13153-y.
[36] M. Everingham, L. Van Gool, C. K. I. Williams, J. Winn, and A. Zisserman, “The pascal visual object classes (VOC) challenge,” Int. J. Comput. Vis., vol. 88, no. 2, pp. 303–338, 2010, doi: 10.1007/s11263-009-0275-4.
[37] J. Kaur, “Tools, techniques, datasets and application areas for object detection in an image: A review,” Multimed. Tools Appl., vol. 81, no. 27, pp. 38297–38351, 2022, doi: 10.1007/s11042-022-13491-9.
[38] J. Mijalkovic and A. Spognardi, “Reducing the False Negative Rate in Deep Learning Based Network Intrusion Detection Systems,” Algorithms, vol. 15, no. 8, 2022, doi: 10.3390/a15080258.
[39] C. Mwitta and G. C. Rains, “Evaluation of Inference Performance of Deep Learning Models for Real-Time Weed Detection in an Embedded Computer,” Sensors, vol. 24, no. 2, pp. 514, 2024, doi: 10.3390/s24020514.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Rangga Pebrianto Rangga, Agus Buono, Heru Sukoco, Aziz Kustiyo, Muhamad Syukur
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
-a.jpg)
-b.jpg)
