IMPLEMENTASI ALGORITMA YOLOV8 DALAM DETEKSI TANAMAN HERBAL BERBASIS DEEP LEARNING
Bilah Samping Artikel
Isi Artikel Utama
Abstrak
Automatic detection of herbal and non-herbal plants is an important challenge in natural resource management and sustainable agriculture, due to visual similarities and morphological variations between plant types. This research aims to develop a real-time herbal and non-herbal plant detection and classification system using the YOLOv8 algorithm, one of the latest deep learning models that excels in detection speed and accuracy. The dataset used consists of 42 plant images, 21 each for herbal and non-herbal classes, which have been manually labeled and processed through the Roboflow platform. The model was trained with several configuration scenarios to obtain optimal performance. The evaluation results showed that the model achieved a mean average precision (mAP) value of 96.6%, precision of 89.3%, and recall of 88.8%. The system is able to detect plant species accurately and efficiently,
and can be implemented directly through Roboflow. This research contributes to the application of deep learning technology in the field of smart agriculture in Indonesia
Rincian Artikel
Referensi
Arisanti, Y.Y., 2021. Mengenali Jenis Tanaman Obat Berbasis Pola Citra Daun dengan Algoritma K-Nearest Neighbors. Jurnal Ilmu Komputer dan Aplikasi (JINACS), 3(2), pp.95–103. https://doi.org/10.26740/jinacs.v3n02.p95-103.
Pinel, A.T.D. et al., 2023. Literasi Penggunaan Obat Herbal yang Aman dan Tepat di Bonto Perak Kabupaten Pangkep. Jurnal Pengabdian Masyarakat Yayasan Insan Cendekia, 2(2). https://doi.org/10.59060/jpmy.v2i2.310.
Golfantara, M.F., 2024. Penggunaan Algoritma YOLOv8 untuk Identifikasi Rempah-Rempah. Jurnal Teknologi dan Teknik, 12(3S1). http://dx.doi.org/10.23960/jitet.v12i3S1.5211.
Siahaan, R.D. et al., 2024. Enhancing Real-time Herbal Plant Detection in Agricultural Environments with YOLOv8. Jurnal Sistem Informasi, 6(4). https://doi.org/10.51519/journalisi.v6i4.889.
Radzi, R. et al., 2022. Machine Learning Algorithms for Herbs Recognition Based on Physical Properties. In: Machine Learning Applications in Data Analysis. 1st ed. pp.12–23. https://doi.org/10.36647/MLAIDA/2022.12.B1.Ch004.
Zophie, J. & Triharminto, H.H., 2023. Implementasi Algoritma You Only Look Once (YOLO) Menggunakan Web Camera untuk Mendeteksi Objek Statis dan Dinamis. Jurnal Pengembangan Bisnis, 1(1). https://doi.org/10.62828/jpb.v1i1.50.
Komputa, 2023. Pelacakan Objek Menggunakan Algoritma YOLOv8 untuk Menghitung Kendaraan. Komputa: Jurnal Ilmiah Komputer dan Informatika, 12(2), pp.91–99. https://doi.org/10.34010/komputa.v12i2.10654.
Astiadewi, E. et al., 2025. Algoritma YOLOv8 untuk Meningkatkan Analisa Gambar dalam Mendeteksi Jerawat. Jurnal Informatika Teknologi dan Sains (Jinteks), 7(1), pp.346–353. https://doi.org/10.51401/jinteks.v7i1.5432.
Prasetya, I.A. et al., 2024. Klasifikasi Kualitas Buah Jeruk Menggunakan Computer Vision dengan Arsitektur YOLOv8. Jurnal Pendidikan Informatika dan Sains, 13(2), pp.187–201. https://doi.org/10.31571/saintek.v13i2.8346.
Azhari, M.F., 2024. Deteksi & Kuantifikasi Trikomatipe Glandular (Bulbose) pada Citra Daun Tanaman Kentang Menggunakan Deep Learning. Universitas Islam Indonesia. https://dspace.uii.ac.id/handle/123456789/54341.
Putra, R., Maimunah, M. & Sasongko, D., 2024. Implementasi Algoritma YOLOv8 (You Only Look Once) dalam Deteksi Penyakit Daun Durian. Gedung Informatika, Teknologi dan Sains (BITS), 6(3), pp.1517–1526. https://doi.org/10.47065/bits.v6i3.6136.
Poerwandono, E. & Barronzoeputra, G.Q., 2024. Implementasi Algoritma You Only Look Once (YOLOv8) untuk Mendeteksi Pelanggaran Lalu Lintas berupa Tidak Menggunakan Helm (Studi Kasus di Jatiasih, Bekasi). Jurnal Indonesia: Manajemen Informatika dan Komunikasi, 5(3), pp.3237–3247. https://doi.org/10.35870/jimik.v5i3.1017.