Deteksi Kematangan dan Kesegaran Tomat Berbasis Web Menggunakan Algoritma YOLOv8
DOI:
https://doi.org/10.69693/ijmst.v4i3.13916Keywords:
Deteksi Kematangan Tomat, Kesegaran Tomat, YOLOv8, Deteksi Objek, Sistem Berbasis WebAbstract
Penyortiran kematangan dan kesegaran tomat secara manual bergantung pada pengamatan visual sehingga berpotensi menghasilkan penilaian yang tidak konsisten dan memperlambat proses distribusi pangan. Penelitian ini bertujuan mengembangkan sistem berbasis web yang mampu mendeteksi kondisi tomat secara otomatis menggunakan algoritma You Only Look Once versi 8 (YOLOv8). Dataset penelitian terdiri atas 1.004 citra dengan 2.427 objek beranotasi yang dikelompokkan ke dalam tiga kelas, yaitu Tomat Segar, Tomat Matang, dan Tomat Tidak Layak. Anotasi objek dilakukan menggunakan bounding box pada platform Roboflow. Data kemudian melalui tahap augmentasi berupa pembalikan horizontal, rotasi, serta penyesuaian hue, kontras, saturasi, kecerahan, dan eksposur sebelum digunakan untuk melatih model. Kinerja deteksi dievaluasi menggunakan precision, recall, mean Average Precision pada ambang Intersection over Union 0,50 (mAP50), mAP50–95, dan confusion matrix. Model menghasilkan precision sebesar 0,924, recall 0,851, mAP50 0,964, dan mAP50–95 0,714. Pengujian confusion matrix pada 214 sampel menghasilkan akurasi keseluruhan 79,9%, dengan precision tertinggi pada kelas Tomat Segar sebesar 83,3% dan recall tertinggi pada kelas Tomat Matang sebesar 92,9%. Model selanjutnya diintegrasikan dengan antarmuka web berbasis HTML, CSS, dan JavaScript, backend PHP, serta modul inferensi Python untuk menampilkan bounding box, label kelas, dan nilai confidence. Hasil penelitian menunjukkan bahwa sistem dapat membantu penyortiran tomat secara lebih cepat dan objektif, meskipun ketepatan lokalisasi objek serta kemampuan menghadapi variasi kondisi nyata masih perlu ditingkatkan.
References
1. Aherwadi, N., Mittal, U., Singla, J., Jhanjhi, N. Z., Yassine, A., & Hossain, M. S. (2022). Prediction of fruit maturity, quality, and its life using deep learning algorithms. Electronics, 11(24), 4100. https://doi.org/10.3390/electronics11244100
2. Baladraf, T. T. (2024). Analisis kerugian pascapanen melalui Commodity System Assessment Method pada komoditas tomat di Indonesia. Prosiding Seminar Nasional Pembangunan dan Pendidikan Vokasi Pertanian, 5(1), 387–396. https://doi.org/10.47687/snppvp.v5i1.1121
3. Bengio, Y., LeCun, Y., & Hinton, G. (2021). Deep learning for AI. Communications of the ACM, 64(7), 58–65. https://doi.org/10.1145/3448250
4. Collins, E. J., Bowyer, C., Tsouza, A., & Chopra, M. (2022). Tomatoes: An extensive review of the associated health impacts of tomatoes and factors that can affect their cultivation. Biology, 11(2), 239. https://doi.org/10.3390/biology11020239
5. Cong, X., Li, S., Chen, F., Liu, C., & Meng, Y. (2023). A review of YOLO object detection algorithms based on deep learning. Frontiers in Computing and Intelligent Systems, 4(2), 17–20. https://doi.org/10.54097/fcis.v4i2.9730
6. Erwanto, B., Pradana, A. I., & Hartanti, D. (2024). Pengembangan sistem deteksi penyakit tanaman tomat melalui citra daun dengan metode You Only Look Once berbasis Android. G-Tech: Jurnal Teknologi Terapan, 8(3), 1453–1463. https://doi.org/10.33379/gtech.v8i3.4327
7. Khan, A., Hassan, T., Shafay, M., Fahmy, I., Werghi, N., Seneviratne, L., & Hussain, I. (2023). Tomato maturity recognition with convolutional transformers. Scientific Reports, 13, 22885. https://doi.org/10.1038/s41598-023-50129-w
8. Kim, T., Lee, D. H., Kim, K. C., Choi, T., & Yu, J. M. (2023). Tomato maturity estimation using deep neural network. Applied Sciences, 13(1), 412. https://doi.org/10.3390/app13010412
9. Li, P., Zheng, J., Li, P., Long, H., Li, M., & Gao, L. (2023). Tomato maturity detection and counting model based on MHSA-YOLOv8. Sensors, 23(15), 6701. https://doi.org/10.3390/s23156701
10. Nahak, P., Pratihar, D. K., & Deb, A. K. (2025). Tomato maturity stage prediction based on vision transformer and deep convolution neural networks. International Journal of Hybrid Intelligent Systems, 21(1), 61–78. https://doi.org/10.3233/HIS-240021
11. Rico, A. L. J. (2025). AI-driven computer vision for automated postharvest quality assessment of Diamante Max tomatoes using YOLOv5. International Journal of Advanced Science and Intelligent Systems, 47–57. https://doi.org/10.29284/18tref64
12. Rismayanti, A., & Rahmadewi, R. (2025). Deteksi dan klasifikasi tingkat kematangan buah mangga harum manis menggunakan You Only Look Once (YOLO) V8. JATI: Jurnal Mahasiswa Teknik Informatika, 9(3), 3645–3654. https://doi.org/10.36040/jati.v9i3.13320
13. Shobaki, W. A., & Milanova, M. (2025). A comparative study of YOLO, SSD, Faster R-CNN, and more for optimized eye-gaze writing. Sci, 7(2), 47. https://doi.org/10.3390/sci7020047
14. Stasenko, N., Shukhratov, I., Savinov, M., Shadrin, D., & Somov, A. (2023). Deep learning in precision agriculture: Artificially generated VNIR images segmentation for early postharvest decay prediction in apples. Entropy, 25(7), 987. https://doi.org/10.3390/e25070987
15. Wang, S., Xiang, J., Chen, D., & Zhang, C. (2024). A method for detecting tomato maturity based on deep learning. Applied Sciences, 14(23), 11111. https://doi.org/10.3390/app142311111
16. Wibowo, A., Lusiana, L., & Dewi, T. K. (2023). Implementasi algoritma deep learning You Only Look Once (YOLOv5) untuk deteksi buah segar dan busuk. Paspalum: Jurnal Ilmiah Pertanian, 11(1), 123–130. https://doi.org/10.35138/paspalum.v11i1.489
17. Xiao, B., Nguyen, M., & Yan, W. Q. (2024). Fruit ripeness identification using YOLOv8 model. Multimedia Tools and Applications, 83, 28039–28056. https://doi.org/10.1007/s11042-023-16570-9
18. Zheng, S., Jia, X., He, M., Zheng, Z., Lin, T., & Weng, W. (2024). Tomato recognition method based on the YOLOv8-Tomato model in complex greenhouse environments. Agronomy, 14(8), 1764. https://doi.org/10.3390/agronomy14081764
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Indonesian Journal of Multidisciplinary on Social and Technology

This work is licensed under a Creative Commons Attribution 4.0 International License.














