Klasifikasi Penyakit Daun Mangga Menggunakan CNN Berbasis Transfer Learning Dengan Model Arsitektur VGG16, DenseNet121, dan InceptionV3
DOI:
https://doi.org/10.30865/jurikom.v13i1.9504Keywords:
Convolutional Neural Network, VGG16, DenseNet121, InceptionV3, Mango Leaf Disease ClassificationAbstract
Mango is one of the important fruits in Indonesia, but its production is often disrupted by leaf diseases and pests that are difficult to detect early. Manual disease recognition methods usually depend on observers and are not always accurate. This study aims to create an automated system to classify mango leaf diseases, using deep learning techniques based on the Convolutional Neural Network (CNN) algorithm. This study also compares three models, namely VGG16, DenseNet121, and InceptionV3, by applying the transfer learning method. The dataset used consists of 4,000 images divided evenly into 8 categories, consisting of 7 types of diseases (Anthracnose, Bacterial Canker, Cutting Weevil, Die Back, Gall Midge, Powdery Mildew, Sooty Mold) and 1 category of healthy plants. Evaluation was carried out using the 5-Fold Cross-Validation method to ensure valid results. The results show that all three models are able to provide an accuracy of more than 90%. The VGG16 model showed the best and most stable performance, with an accuracy of 93.25%, a Precision of 0.93, a Recall of 0.93, an F1-Score of 0.93, and an AUC-ROC of 0.98. Meanwhile, InceptionV3 achieved an accuracy of 92.38% and DenseNet121 reached 91.25%. Therefore, VGG16 is recommended as the primary model due to its better ability to extract texture features and accurately recognize mango leaf diseases. VGG16 architecture is able to outperform complex models in efficiently extracting mango leaf texture features, making it very potential to be used as a basis for real-time plant disease diagnosis applications for farmers
References
[1] E. J. Warschefsky, “Population genomic analysis of mango ( Mangifera indica ) suggests a complex history of domestication,” no. 2019, pp. 2023–2037, 2023, doi: 10.1111/nph.15731.
[2] K. Futri Ramadhani and M. Tarigan, “Implementasi Metode Convolutional Neural Network Untuk Klasifikasi Penyakit Daun Mangga Menggunakan Arsitektur Efficientnetv2-S Dan Resnet50,” JATI (Jurnal Mhs. Tek. Inform., vol. 9, no. 3, pp. 4135–4143, 2025, doi: 10.36040/jati.v9i3.13571.
[3] A. K. Dofuor et al., “Mango anthracnose disease: the current situation and direction for future research,” Front. Microbiol., vol. 14, no. August, pp. 1–18, 2023, doi: 10.3389/fmicb.2023.1168203.
[4] rahayu deny danar dan alvi furwanti Alwie, A. B. Prasetio, R. Andespa, P. N. Lhokseumawe, and K. Pengantar, “Tugas Akhir Tugas Akhir,” J. Ekon. Vol. 18, Nomor 1 Maret201, vol. 2, no. 1, pp. 41–49, 2024.
[5] B. Paneru, B. Paneru, and K. B. Shah, “Analysis of Convolutional Neural Network-based Image Classifications: A Multi Featured Application for Rice Leaf Disease Prediction and Recommendations for Farmers,” vol. 6, no. 3, pp. 174–187, 2024.
[6] S. Dwi Anggraeni, E. Yulia Puspaningrum, and A. Lina Nurlaili, “Klasifikasi Penyakit Daun Mangga Menggunakan Anfis,” JATI (Jurnal Mhs. Tek. Inform., vol. 9, no. 3, pp. 5467–5473, 2025, doi: 10.36040/jati.v9i3.14311.
[7] A. Rajbongshi, T. Khan, M. Rahman, A. Pramanik, and S. Tanvir, “Recognition of mango leaf disease using convolutional neural network models : a transfer learning approach,” vol. 23, no. 3, pp. 1681–1688, 2021, doi: 10.11591/ijeecs.v23.i3.pp1681-1688.
[8] Y. Agegnehu, A. Melese, B. Mulugeta, T. Nigussie, E. Ayenew, and T. Endeshaw, “Smart Agricultural Technology Classification of mango disease using ensemble convolutional neural network,” Smart Agric. Technol., vol. 8, no. May, p. 100476, 2024, doi: 10.1016/j.atech.2024.100476.
[9] T. Ayu, V. Dwi, and A. E. Minarno, “Pendiagnosa Daun Mangga Dengan Model Convolutional Neural Network,” CESS (Journal Comput. Eng. Syst. Sci., vol. 6, no. 2, p. 230, 2021, doi: 10.24114/cess.v6i2.22857.
[10] P. D. Rinanda, D. N. Aini, and T. A. Pertiwi, “Implementation of Convolutional Neural Network ( CNN ) for Image Classification of Leaf Disease In Mango Plants Using Deep Learning Approach,” vol. 1, no. January, pp. 55–61, 2024.
[11] A. R. Auni and E. Sugiharti, “Optimization of Mango Plant Leaf Disease Classification Using Concatenation Method of MobileNetV2 and DenseNet201 CNN Architectures,” vol. 11, no. 4, pp. 1023–1034, 2024, doi: 10.15294/sji.v11i4.15169.
[12] M. J. Setiawan, B. Nugroho, and A. P. Sari, “Klasifikasi Penyakit Daun Tanaman Menggunakan Algoritma CNN dan Random Forest,” vol. 12, no. 1, pp. 1–7, 2023.
[13] 6 · Xia Zhao1 · Limin Wang1 · Yufei Zhang2 · Xuming Han3 · Muhammet Deveci4, 5 and M. Parmar7, “A review of convolutional neural networks in computer vision,” 2024.
[14] B. U. Mahmud, A. Al Mamun, J. Hossen, G. Y. Hong, and B. Jahan, “Light-Weight Deep Learning Model for Accelerating the Classification of Mango-Leaf Disease,” vol. 8, no. 1, pp. 28–42, 2024.
[15] E. Rayed, J. R. Jim, J. Islam, and M. F. M. Senior, “MangoLeafXNet : An Explainable Deep Learning Model for Accurate Mango Leaf Disease Classification,” IEEE Access, vol. PP, p. 1, 2025, doi: 10.1109/ACCESS.2025.3571450.
[16] Z. Jiang, Y. Liu, Z. Shao, and K. Huang, “applied sciences An Improved VGG16 Model for Pneumonia Image Classification,” 2021.
[17] R. Ardiansyah, M. Ayu, D. Widyadara, and U. Mahdyah, “Deteksi Penyakit Daun Mangga Menggunakan Convolutional Neural Network Untuk Analisis Komperasi Arsitektur VGG16, Xception,” Inotek, vol. 9, pp. 2549–7952, 2025.
[18] Y. Zhang, C. Ning, and W. Yang, “An automatic cervical cell classification model based on improved DenseNet121,” pp. 1–18, 2025.
[19] A. Sharma and R. Parvathi, “Enhancing Cervical Cancer Classification : Through a Hybrid Deep Learning Approach Integrating,” IEEE Access, vol. 13, no. January, pp. 9868–9878, 2025, doi: 10.1109/ACCESS.2025.3527677.
[20] A. Nurdin, D. Satria, Y. Kartika, A. Rezha, and E. Najaf, “Klasifikasi Penyakit Daun Tomat Dengan Metode Convolutional Neural Network Menggunakan Arsitektur Inception-V3,” no. 1, pp. 1–6, 2024.
[21] S. N. & A. M. Ferdin Joe John Joseph, “Keras and TensorFlow: A Hands-On Experience,” 2021.
[22] M. Reyad and A. M. Sarhan, “A modified Adam algorithm for deep neural network optimization,” Neural Comput. Appl., vol. 35, no. 23, pp. 17095–17112, 2023, doi: 10.1007/s00521-023-08568-z.
[23] J. Li, “Asymptotics of K-Fold Cross Validation,” vol. 78, pp. 491–526, 2023.
[24] Z. A. Sejuti and S. Islam, “A hybrid CNN – KNN approach for identi fi cation of COVID-19 with 5-fold cross validation,” Sensors Int., vol. 4, no. November 2022, p. 100229, 2023, doi: 10.1016/j.sintl.2023.100229.
[25] M. S. Uzer, “Deep Learning-Based Classification Consisting of Pre-Trained Models and Proposed Model Using K-Fold Cross-Validation for Pistachio Species,” 2025.
[26] J. K. & S. Mukherjee, “Impact of Autotuned Fully Connected Layers on Performance of Self-supervised Models for Image Classification,” 2024.
[27] L. Anghel, Manon Dampfhoffer, Thomas Mesquida, Alexandre Valentian, “Backpropagation-Based Learning Techniques for Deep Spiking Neural Networks: A Survey,” 2023.
[28] L. Risqia and Z. Fatah, “Jamastika, volume 4 nomor 1 april 2025,” vol. 4, no. April, pp. 102–107, 2025.
