Deep Learning-Based CNN for Tea Leaf Disease Classification
DOI:
https://doi.org/10.59934/jaiea.v5i1.1724Keywords:
Deep Learning, DenseNet121, Tea Leaves, Image Classification, Plant Diseases, Transfer Learning.Abstract
Tea leaf diseasve is one of the main factors affecting the quality and quantity of tea plant production. Early detection and accurate classification of leaf disease types are essential to prevent wider damage. This study aimed to develop a digital image-based tea leaf disease classification system using the DenseNet121 architecture with a Transfer Learning approach. The tea leaf image dataset used came from the Kaggle platform, which consisted of eight classes: Algal Leaf, Anthracnose, Bird Eye Spot, Brown Blight, Gray Blight, Red Leaf Spot, White Spot, and Healthy.
The model was developed through four training scenarios with varying numbers of epochs (20, 40, 60, and 80) to evaluate the effect of training duration on classification performance. The macro average approach was used to evaluate each scenario using accuracy, precision, recall, and F1-score metrics. The best results were obtained in scenario 4 (Epoch 80), with an accuracy of 92.57%, macro precision 92.91%, macro recall 92.49%, and macro F1-score 92.47%. These results indicated that DenseNet121 was able to classify tea leaf diseases effectively and accurately.
This study demonstrates the potential of the DenseNet architecture as a Deep Learning-based solution in detecting plant diseases and opens up opportunities for the development of decision support systems in agriculture.
Downloads
References
K. D. A. Puspita, A. Nilogiri, and H. Oktavianto, “Deteksi Penyakit Daun Teh Menggunakan Metode Convolutional Neural Network (CNN),” J. Apl. Sist. Inf. dan Elektron., vol. 5, no. 1, pp. 45–50, 2023.
Y. A. Suwitono and F. J. Kaunang, “Implementasi Algoritma Convolutional Neural Network (CNN) Untuk Klasifikasi Daun Dengan Metode Data Mining SEMMA Menggunakan Keras,” J. Komtika (Komputasi dan Inform., vol. 6, no. 2, pp. 109–121, 2022, doi: 10.31603/komtika.v6i2.8054.
A. T. Rahman, A. Setyanto, and H. Al Fatta, “Klasifikasi Penyakit Daun Apel Menggunakan Arsitektur CNN dengan Transfer Learning,” J. SENOPATI Sustain. Ergon. Optim. Appl. Ind. Eng., vol. 6, no. 1, pp. 42–49, 2024, doi: 10.31284/j.senopati.2024.v6i1.6574.
N. IBRAHIM et al., “Klasifikasi Tingkat Kematangan Pucuk Daun Teh menggunakan Metode Convolutional Neural Network,” ELKOMIKA J. Tek. Energi Elektr. Tek. Telekomun. Tek. Elektron., vol. 10, no. 1, p. 162, 2022, doi: 10.26760/elkomika.v10i1.162.
R. Faurina, S. Rahma, A. Vatresia, and A. Susanto, “Comparison of Convolutional Neural Networks Transfer Learning Models for Disease Classification of Food Crops,” Int. J. Informatics Vis., vol. 8, no. 4, pp. 2020–2032, 2024, doi: 10.62527/joiv.8.4.1936.
Purwono, A. Ma’arif, W. Rahmaniar, H. I. K. Fathurrahman, A. Z. K. Frisky, and Q. M. U. Haq, “Understanding of Convolutional Neural Network (CNN): A Review,” Int. J. Robot. Control Syst., vol. 2, no. 4, pp. 739–748, 2022, doi: 10.31763/ijrcs.v2i4.888.
A. Hidayat and T. Ernawati, “Metode Klasifikasi Algoritma Convolutional Neural Network (CNN) pada Penyakit Daun Teh,” J. Inf. dan Komput., vol. 12, no. 2, pp. 97–102, 2024.
E. Oktafanda, “Klasifikasi Citra Kualitas Bibit dalam Meningkatkan Produksi Kelapa Sawit Menggunakan Metode Convolutional Neural Network (CNN),” J. Inform. Ekon. Bisnis, vol. 4, no. 3, pp. 72–77, 2022, doi: 10.37034/infeb.v4i3.143.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Journal of Artificial Intelligence and Engineering Applications (JAIEA)
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
