Perancangan Aplikasi Computer Vision Berbasis Convolutional Neural Network Untuk Deteksi Kematangan Kelapa Sawit
DOI:
https://doi.org/10.33998/jakakom.2026.6.1.2568Keywords:
Oil Palm, Fruit Maturity, Computer Vison, Convutional Neural Network, YOLOv5, ApplicationAbstract
Manual determination of oil palm fruit maturity remains a significant challenge for farmers, leading to inefficiencies and reduced harvest quality. This research aims to design and implement a computer vision application based on Convolutional Neural Network (CNN) to automatically, objectively, and efficiently detect oil palm fruit maturity. The methodology involves web-based system development using the Waterfall model, integrating a modified YOLOv5s architecture enhanced with a Convolutional Block Attention Module (CBAM), C3 Transformer (C3TR), and Bidirectional Feature Pyramid Network (BiFPN). A dataset of 4160 oil palm fruit images underwent auto-orient, resize, color normalization, and data augmentation, then split into 70% training, 20% validation, and 10% test sets. Model training was conducted on Google Colab using an Nvidia A100 GPU for 21.36 minutes. Evaluation results demonstrate very high performance with a Precision of 0.9858, Recall of 0.9910, [email protected] of 0.9941, and [email protected]:0.95 of 0.8544. The Confusion Matrix and Precision-Recall curve indicate excellent classification accuracy and strong model generalization capabilities. The web-based system allows farmers to upload images or videos and use a webcam for real-time detection. This application is expected to assist farmers in identifying oil palm fruit maturity more quickly and objectively, minimizing errors, and improving harvest quality and efficiency.
Downloads
References
B. H. Simanjuntak, “Analisis produktivitas perkebunan kelapa sawit di Sumatera dan Kalimantan,” Jurnal Ekonomi dan Bisnis Perkebunan, vol. 8, no. 1, pp. 30–45, 2020.
A. Hasibuan, F. Siregar, and M. Hidayat, “Pengaruh Tingkat Kematangan Tandan Buah Segar (TBS) terhadap Rendemen dan Mutu Minyak Kelapa Sawit,” Jurnal Ilmu dan Teknologi Perkebunan, vol. 18, no. 3, pp. 112–128, 2022.
S. Hidayat and E. Nurhayati, “Studi kasus kesalahan panen pada perkebunan kelapa sawit rakyat,” Jurnal Agroekoteknologi, vol. 14, no. 2, pp. 78–90, 2021.
P. R. Kumar, A. R. Singh, and M. R. K. Varma, “The role of artificial intelligence and computer vision in modern agriculture: A comprehensive review,” Journal of Agricultural Technology and Innovation, vol. 5, no. 2, pp. 45–58, 2021.
L. P. Sari, D. P. Wardani, and S. M. Susanto, “Aplikasi computer vision dalam berbagai sektor industri: studi kasus di bidang kesehatan, manufaktur, dan transportasi,” Jurnal Teknologi Informasi, vol. 15, no. 4, pp. 345–360, 2022.
S. Wahyuni and Y. Sulaeman, “Penerapan Deep Learning untuk Prediksi Harga Saham Menggunakan Metode Long Short-Term Memory (LSTM),” Jurnal Sistem Informasi Bisnis, vol. 12, no. 2, pp. 150–160, 2022.
B. T. Nugroho, “Aplikasi convolutional neural network (CNN) dalam klasifikasi objek di bidang pertanian: review dan prospek,” Jurnal Ilmu Komputer dan Informasi, vol. 16, no. 1, pp. 1–15, 2021.
F. B. Setiawan, C. B. Adipradana, and L. H. Pratomo, “Fruit Ripeness Classification System Using Convolutional Neural Network (CNN) Method,” Protek: Jurnal Ilmiah Teknik Elektro, vol. 10, no. 1, p., 2023, doi: 10.33387/protk.v10i1.5549.
B. Xiao, M. Nguyen, and W. Q. Yan, “Apple Ripeness Identification Using Deep Learning,” 2021. doi: 10.1007/978-3-030-.
M. Rifqi and E. Suharjito, “Deteksi tingkat kematangan buah sawit berdasarkan komposisi warna menggunakan convolutional neural network,” Jurnal Sains dan Teknologi Komputer, vol. 15, no. 2, pp. 170–185, 2021.
A. Syaifuddin, R. Wibowo, and D. Pratama, “Identifikasi Tingkat Kematangan Buah Kelapa Sawit Menggunakan Convolutional Neural Network (CNN) untuk Panen yang Efisien,” Jurnal Teknologi Pertanian, vol. 24, no. 1, pp. 50–65, 2023.
S. Maysaroh, H. Purnomo, and A. Fitriani, “Identifikasi Kematangan Buah Sawit Berdasarkan Ekstraksi Warna RGB dan HSV Menggunakan Metode K-Means Clustering,” Jurnal Informatika Terapan, vol. 15, no. 2, pp. 88–102, 2021.
D. Kurniawan, M. T. Handoko, and J. Prayoga, “Sistem klasifikasi kematangan buah sawit menggunakan YOLOv5 dan dataset citra,” Jurnal Teknologi dan Komputer Terapan, vol. 13, no. 1, pp. 45–56, 2022.
A. Arsyad, R. Nugraha, and F. A. Ramadhan, “Pengembangan sistem deteksi kematangan buah sawit secara real-time menggunakan YOLOv4 dan video,” Jurnal Informatika, vol. 17, no. 3, pp. 210–225, 2022.
E. Kurniawan, D. Saputra, and R. Ariyanto, “Performa convolutional neural network dalam klasifikasi tingkat kematangan buah apel dan tomat,” Jurnal Komputasi Pertanian, vol. 7, no. 4, pp. 290–305, 2019.
A. Arsyad, R. Nugraha, and F. A. Ramadhan, “Sistem Deteksi Kematangan Buah Kelapa Sawit Secara Real-Time Menggunakan Arsitektur YOLOv4 untuk Aplikasi Mobile dan Web,” Jurnal Informatika, vol. 17, no. 3, pp. 201–215, 2023.
M. R. Fadli, S. A. Ginting, and R. F. Pratama, “Analisis tantangan dan solusi dalam pengumpulan dataset untuk deep learning pada objek pertanian,” Jurnal Sistem Cerdas, vol. 11, no. 2, pp. 140–155, 2020.
binus, “sawit Object Detection Model (v5),” 2022.
R. S. Pressman and B. R. Maxim, “Software Engineering.” 2020.
