Optimalisasi Deteksi Tingkat Kematangan Tanda Buah Segar Kelapa Sawit Menggunakan YOLOV8 Dengan Platform Web

Iffatul Mardhiyah; Dyan Prawita Sari; Zahwa Genoveva; Rifki Kosasih; Dyah Cita Irawati

doi:10.35760/tr.2025.v30i3.67

Authors

Iffatul Mardhiyah Gunadarma University Author
Dyan Prawita Sari Gunadarma University Author
Zahwa Genoveva Gunadarma University Author
Rifki Kosasih Gunadarma University Author
Dyah Cita Irawati Gunadarma University Author

DOI:

https://doi.org/10.35760/tr.2025.v30i3.67

Keywords:

CRISP-DM, fresh fruit bunches (FFB), machine learning, object detection, YOLOv8

Abstract

Oil palm represents one of Indonesia’s principal commodities. Traditionally, farmers manually monitor the ripeness level of palm oil, but this method is neither effective nor efficient for large-scale harvests. Therefore, a system that can automatically detect the ripeness level of fresh fruit bunches (FFB) is needed. In this study, the YOLOv8 algorithm was used which was integrated into a web-based application. The system is designed to improve accuracy and efficiency in the grading process of oil palm fruits, which directly impacts the quality of processed products and palm oil production. The dataset used consists of 6.592 images obtained through the Roboflow platform, covering various ripeness categories. The system development follows the CRISP-DM approach, consisting of business understanding, data understanding, data preparation, modeling, evaluation and deployment. The model training process approximately 3,1 hours, with evaluation results showing a precision of 94,5%, recall of 94,7%, and a mean Average Precision (mAP) of 98%. The model’s performance is further supported by an F1-confidence curve of 95% and a precision-recall curve of 98%, indicating stable and accurate classification capabilities. The model is deployed through a Streamlit-based web interface, allowing users to perform real-time detection from images or videos without requiring additional installations.

Downloads

Download data is not yet available.

References

[1] W. E. Sari, Muslimin, A. Franz, and P. Sugiartawan, “Deteksi tingkat kematangan tandan buah segar kelapa sawit dengan k-means,” Sintech J., vol. 5, no. 2, pp. 154–164, 2022, doi: 10.31598/sintechjournal.v5i2.1146.

[2] J. Yu, G. Yusri, Y. Mohamed, and S. Mohamed, “Fresh fruit bunch ripeness classification methods: A review,” Food Bioprocess Technol., vol. 18, pp. 183–206, 2025, doi: 10.1007/s11947-024-03483-0.

[3] Badan Pusat Statistik (BPS) Republik Indonesia, Statistik Kelapa Sawit Indonesia 2023. Jakarta: BPS, 2024.

[4] N. Sari, M. Shiddiq, R. Hayu, and N. Zakyyah, “Klasifikasi tingkat kematangan tandan buah segar kelapa sawit menggunakan probe optik,” J. Aceh Phys. Soc., vol. 8, no. 3, pp. 72–77, 2019, doi: 10.24815/jacps.v8i3.14122.

[5] M. Rifqi and Suharjito, “Deteksi kematangan Tanda Buah Segar (TBS) kelapa sawit berdasarkan komposisi warna menggunakan deep learning,” J. Tek. Inform., vol. 14, no. 2, pp. 125–134, 2021, doi: 10.15408/jti.v14i2.23295.

[6] K. A. Bagaskara and E. Seniwati, “Identifikasi tingkat kematangan buah tomat dengan citra warna,” Inf. Technol. J., vol. 5, no. 1, pp. 1–10, 2023, doi: 10.24076/intechnojournal.2023v5i1.1575.

[7] K. U. Putra, W. Yosfand, and A. Ramadhanu, “Klasifikasi kematangan buah pepaya berdasarkan warna menggunakan convolutional neural network,” J. Ilm. Teknol. Sist. Inf., vol. 6, no. 1, pp. 1–6, 2025, doi: 10.62527/jitsi.

[8] M. Aksa, A. Ranggareksa, A. B. Kaswar, D. Darma, and R. Nurul, “Deteksi tingkat kematangan buah mangga berdasarkan fitur warna menggunakan pengolahan citra digital,” J. Tek. Inform. dan Sist. Inf., vol. 11, no. 2, pp. 240–250, 2025, doi: 10.28932/jutisi.v11i2.10578.

[9] C. D. Pangati, G. Hoendarto, and Hendro, “Klasifikasi kematangan buah sawit berbasis website menggunakan deep learning,” J. Widyadharma, vol. 10, pp. 1–11, 2025.

[10] A. Rahmawati, M. Akbar, and D. Nurdiansyah, “Klasifikasi tingkat kematangan pada buah kelapa sawit berbasis deep learning,” in Proceedings Economic, Social Science, Computer, Agriculture and Fisheries (ESCAF) 4th 2025, 2025, pp. 1064–1073.

[11] R. Triyogi, R. Magdalena, and B. Hidayat, “Mendeteksi kematangan buah kelapa sawit menggunakan convolution neural network deep learning,” J. Nas. Sains Tek., vol. 1, no. 1, pp. 22–27, 2023, doi: 10.25124/logic.v1i1.6732.

[12] R. Kurniawan, A. T. Martadinata, and S. D. Cahyo, “Klasifikasi tingkat kematangan buah sawit berbasis deep learning dengan menggunakan arsitektur yolov5,” J. Inf. Syst. Res., vol. 5, no. 1, pp. 302–309, 2023, doi: 10.47065/josh.v5i1.4408.

[13] S. Aras, P. Tanra, and M. Bazhar, “Deteksi tingkat kematangan buah tomat menggunakan yolov5,” Indones. J. Mach. Learn. Comput. Sci., vol. 4, no. 2, pp. 623–628, 2024, doi: 10.57152/malcom.v4i2.1270.

[14] I. G. Khresna, N. P. Sutramiani, and N. K. Ayu Wirdiani, “Network reduction strategy on yolov8 model for mango leaf disease detection,” J. Buana Inform., vol. 16, no. 2, pp. 124–133, 2025.

[15] M. Shiddiq, L. B. Sitohang, I. R. Husein, and S. A. Ningsih, “Hidung elektronik berbasis sensor gas mos untuk karakterisasi kematangan buah kelapa sawit,” J. Tek. Pertan. Lampung, vol. 10, no. 2, pp. 170–182, 2021, doi: 10.23960/jtep-l.v10i2.170-182.

[16] Syaddam, S. D. Soeksin, and R. Nizar, “Teknologi computer vision untuk melakukan deteksi dan penentuan kualitas bibit ayam day old chicks,” J. Inform. J. Pengemb. IT, vol. 9, no. 3, pp. 296–305, 2024, doi: 10.30591/jpit.v9i3.7923.

[17] J. Subur, Suryadhi, M. Taufiqurrohman, and N. R. Al Hafizh, “Pemanfaatan teknologi computer vision untuk deteksi ukuran ikan bandeng dalam membantu proses sortir ikan,” J. Tek. Elektro, vol. 7, no. 01, pp. 52–60, 2024, doi: 10.30651/cl.v7i01.21239.

[18] D. Pakiding, A. Selao, and Wahyuddin, “Implementasi computer vision dalam mendeteksi penyakit pada tanaman cabai dan tomat menggunakan algoritma convolutional neural networks,” Indones. J. Mach. Learn. Comput. Sci., vol. 5, no. 3, pp. 841–850, 2025, doi: 10.57152/malcom.v5i3.1989.

[19] O. W. Wijaya, D. R. Manday, A. Napitupulu, M. Turnip, and S. Manurung, “Identifikasi tingkat kematangan buah pada tanaman kelapa sawit menggunakan algoritma convolutional neural network dan pendekatan deep learning,” J. Tugas Akhir Manaj. Inform. Komputerisasi Akunt., vol. 4, no. 2, pp. 232–240, 2024, doi: 10.46880/tamika.Vol4No2(SEMNASTIK).pp232-240.

[20] I. Budiman, T. Prahasto, and Y. Christyono, “Data clustering menggunakan metodologi CRISP-DM untuk pengenalan pola proporsi pelaksanaan tridharma,” 2012, doi: 10.21456/vol1iss3pp129-134.

[21] Roboflow, “Palm Oil Fresh Fruit Bunch Ripeness Dataset,” Roboflow Universe, 2024. [Online]. Available: https://app.roboflow.com/zah/palm-oil-2-1gztp/models. Accessed: Jun. 2025.

[22] S. Yulianto, N. F. Amani, F. Akhyar, and K. Usman, “Sistem inspeksi permukaan baja berbasis deep learning menggunakan metode anchor-free,” J. Ilm. Tek. Mesin, Elektro dan Komput., vol. 2, no. 3, pp. 184–190, 2022, doi: 10.51903/juritek.v2i3.364.

[23] Suriansyah, A. I. Rachman, L. Fanani, A. Halid, and G. Pratiwi, “Peningkatan kinerja database melalui teknik batch loading dan parallel processing pada proses load data,” J. Ilm. Sist. Inf. dan Tek. Inform., vol. 7, no. 1, pp. 146–153, 2024, doi: 10.57093/jisti.v7i1.199.

[24] R. Kosasih, Sudaryanto, and A. Fahrurozi, “Classification of six banana ripeness levels based on statistical features on machine learning approach,” Int. J. Adv. Appl. Sci., vol. 12, no. 4, pp. 317–326, 2023, doi: 10.11591/ijaas.v12.i4.pp317-326.

[25] R. Kosasih and A. Alberto, “Sentiment analysis of game product on shopee using the TF-IDF method and naive bayes classifier,” Ilk. J. Ilm., vol. 13, no. 2, pp. 101–109, 2021, doi: 10.33096/ilkom.v13i2.721.101-109.

[26] S. Clara, D. L. Prianto, R. Al Habsi, E. F. Lumbantobing, and N. Chamidah, “Implementasi seleksi fitur pada algoritma klasifikasi machine learning untuk prediksi penghasilan pada adult income dataset,” in Seminar Nasional Mahasiswa Ilmu Komputer dan Aplikasinya (SENAMIKA), 2021, April, pp. 741–747.

[27] P. L. Romadloni, B. A. Kusuma, and W. M. Baihaqi, “Komparasi metode pembelajaran mesin untuk implementasi pengambilan keputusan dalam menentukan promosi jabatan karyawan,” Jurnal Mhs. Tek. Inform., vol. 6, no. 2, pp. 622–628, 2022, doi: 10.36040/jati.v6i2.5238.

[28] R. Kosasih and M. Arfiansyah, “Pendeteksian kendaraan dengan menggunakan metode running average background substraction dan morfologi citra,” J. Media Inform. Budidarma, vol. 4, no. 4, pp. 979–985, 2020, doi: 10.30865/mib.v4i4.2315.