Klasifikasi Penyakit Daun Anggur Menggunakan Metode CNN Berbasis Arsitektur EfficientNetB6
Pendekatan Deep Learning untuk Deteksi Dini Penyakit Daun Anggur
Keywords:
Tanaman Anggur, Penyakit Daun, CNN, EfficientNetB6, Klasifikasi CitraAbstract
Vitis vinifera atau tanaman anggur merupakan komoditas bernilai ekonomi tinggi yang mudah terserang berbagai penyakit daun, di antaranya Black Rot, Black Measles, dan Leaf Blight, selain kategori daun sehat (Healthy Leaves). Deteksi penyakit secara manual sering kali memerlukan waktu lama dan bersifat subjektif, sehingga diperlukan sistem otomatis berbasis pengolahan citra digital dan deep learning. Penelitian ini bertujuan mengembangkan model klasifikasi penyakit daun anggur dengan empat kelas menggunakan arsitektur Convolutional Neural Network (CNN) EfficientNetB6. Dataset yang digunakan berasal dari Grape400 di Kaggle dan diperluas melalui augmentasi menjadi tiga kali lipat dari jumlah aslinya. Model dilatih selama 50 epoch dengan optimizer Adam dan learning rate 1×10⁻⁴. Berdasarkan hasil pengujian terhadap data uji, model memperoleh akurasi keseluruhan sebesar 98,8% serta nilai rata-rata makro untuk precision, recall, dan f1-score sebesar 0,988, yang menandakan konsistensi performa klasifikasi pada seluruh kelas. Kelas HealthyGrapes terdeteksi sempurna, sedangkan LeafBlight mendekati sempurna, dan kelas BlackMeasles serta BlackRot masing-masing mempertahankan nilai f1-score 0,977. Hasil ini menunjukkan bahwa EfficientNetB6 mampu mengekstraksi fitur morfologis dan tekstural daun anggur secara efektif, serta memiliki kemampuan generalisasi tinggi tanpa indikasi overfitting. Pendekatan ini berpotensi dikembangkan menjadi sistem bantu keputusan untuk deteksi dini penyakit daun anggur berbasis citra digital.
References
A. Khadatkar et al., “A comprehensive review on grapes (Vitis spp.) cultivation and its crop management,” Discov. Agric., vol. 3, no. 1, 2025, doi: 10.1007/s44279-025-00162-2.
X. Xie, Y. Ma, B. Liu, J. He, S. Li, and H. Wang, “A Deep- Learning-Based Real-Time Detector for Grape Leaf Diseases Using Improved Convolutional Neural Networks,” Front. Plant Sci., vol. 11, no. June, pp. 1– 14, 2020, doi: 10.3389/fpls.2020.00751.
P. G. Aher, V. Sabnis, and J. K. Jain, “Deep learning for grape leaf disease detection: A review,” Multidiscip. Rev., vol. 8, no. 11, pp. 1–14, 2025, doi: 10.31893/multirev.2025364.
F. Atesoglu and H. Bingol, “The Detection and Classification of Grape Leaf Diseases with an Improved Hybrid Model Based on Feature Engineering and AI,” AgriEngineering, vol. 7, no. 7, pp. 1–13, 2025, doi: 10.3390/agriengineering7070228.
S. A. Wagle, R. Harikrishnan, S. H. M. Ali, and M. Faseehuddin,
“Classification of plant leaves using new compact convolutional neural network models,” Plants, vol. 11, no. 1, pp. 1–25, 2022, doi: 10.3390/plants11010024.
M. P. Mathew, “A comparative deep learning framework for grape leaf disease classification using EfficientNetB0, InceptionV3, and Xception,” Discov. Appl. Sci., vol. 7, no. 10, 2025, doi: 10.1007/s42452-025-07457-5.
M. A. Hasan, Y. Riyanto, and D. Riana, “Grape leaf image disease classification using CNN-VGG16 model,” J. Teknol. dan Sist. Komput., vol. 9, no. 4, pp. 218–223, 2021, doi: 10.14710/jtsiskom.2021.14013.
A. Y. Darmawan, Y. M. P. Tanga, and J. Unjung, “Grape leaf disease classification using efficientnet feature extraction and catboostclassifier,” J. Soft Comput. Explor., vol. 6, no. 1, pp. 1–8, 2025, doi: 10.52465/joscex.v6i1.507.
B. Liu, Z. Ding, L. Tian, D. He, S. Li, and H. Wang, “Grape Leaf Disease Identification Using Improved Deep Convolutional Neural Networks,” Front. Plant Sci., vol. 11, no. July, pp. 1–14, 2020, doi: 10.3389/fpls.2020.01082.
Barbedo and J. G. Arnal, “Digital Image Processing for Detecting and Classifying Plant Diseases,” Circ. Comput. Sci., vol. 2, no. 11, pp. 1–7, 2017, doi: 10.22632/ccs-2017-252-66.
J. A. Gómez-Camperos, H. Y. Jaramillo, and G. Guerrero-Gómez, “Digital image processing techniques for detection of pests and diseases in crops: a review.,” Ing. y Compet., vol. 24, no. 1, pp. 1–17, 2022, doi: 10.25100/iyc.24i1.10973.
I. Kunduracioglu and I. Pacal, “Advancements in deep learning for accurate classification of grape leaves and diagnosis of grape diseases,” J. Plant Dis. Prot., vol. 131, no. 3, pp. 1061–1080, 2024, doi: 10.1007/s41348- 024-00896-z.
V. Terisia et al., “Comparison of EfficientNet B5-B6 for Detection of 29 Diseases of Fruit Plants,” Sainteks, vol. 20, no. 2, pp. 107–118, 2023, doi: 10.30595/sainteks.v20i2.18691.
J. Lu, L. Tan, and H. Jiang, “Review on convolutional neural network (CNN) applied to plant leaf disease classification,” Agric., vol. 11, no. 8, pp. 1–18, 2021, doi: 10.3390/agriculture11080707.
M. Tan and Q. V. Le, “EfficientNet: Rethinking model scaling for convolutional neural networks,” 36th Int. Conf. Mach. Learn. ICML 2019, vol. 2019-June, pp. 10691–10700, 2019.
R. Akınca, H. Fırat, and M. E. Asker, “Automated Fault Classification in Solar Panels Using Transfer Learning with EfficientNet and ResNet Models,” Eur. J. Tech., vol. 14, no. 2, pp. 164–173, 2024, [Online]. Available: https://dergipark.org.tr/en/pub/ejt/issue/89949/1533783
