Multi-Class Classification of Rice Leaf Diseases Using MobileNetV2 Architecture with Transfer Learning
DOI:
https://doi.org/10.30871/jaic.v10i2.12499Keywords:
Deep Learning, Image Classification, Mobilenetv2, Rice Leaf Disease, Transfer LearningAbstract
Rice leaf diseases are a major cause of yield loss and remain a persistent challenge in agriculture. Conventional diagnosis through visual inspection is subjective and time-consuming, necessitating an accurate and efficient automated system for early detection. This study develops and evaluates a multi-class rice leaf disease classifier based on digital images using MobileNetV2 with transfer learning and fine-tuning of the last 20 layers. The dataset comprises 6,180 images distributed equally across four classes brown spot, leaf blast, leaf blight, and normal with an imbalance ratio of 1.00:1, split into 70% training, 15% validation, and 15% testing using stratified random sampling. The methodology incorporates image normalization, adaptive data augmentation, and class weighting as preventive regularization strategies. The model achieves 97.20% overall test accuracy, with precision of 97.30%, recall of 97.09%, F1-score of 97.19%, and AUC of 99.72%, converging optimally at epoch 25 across 30 training epochs. Per-class accuracy ranges from 96.12% (brown spot) to 97.84% (leaf blast and normal), with misclassifications primarily occurring between visually similar disease classes. With a compact model size of 9.89 MB (FP32) reducible to 2.71 MB via TFLite conversion, and an average inference time of 144.80 ms per image, the proposed model demonstrates high efficiency and strong generalization, making it well-suited for deployment on mobile devices as a practical tool for real-time early rice disease detection in field settings.
Downloads
References
[1] C. Leiwakabessy, F. Inayati, E. Jambormias, J. Patty, and R. E. Ririhena, “Ketahanan Enam Varietas Padi Terhadap Penyakit Blas (Pyricularia oryzae Cav.) pada Lahan Sawah Irigasi dan Sawah Tadah Hujan,” Jurnal Budidaya Pertanian, vol. 16, no. 2, pp. 147–156, 2020, doi: 10.30598/jbdp.2020.16.2.147.
[2] B. H. Isnawan and A. N. Gumilar, “Selection of Intermittent Irrigation to Increase Growth and Yield of Some Local Rice Varieties (Oryza sativa L.) in the Rainy Season,” Jurnal Ilmiah Multidisiplin Indonesia, vol. 2, 2023, doi: 10.58471/esaprom.
[3] M. Irvai and D. Mahdalena, “Penerapan Teknik Masking dan Augmentasi pada Arsitektur CNN dan MobileNetV2 untuk Klasifikasi Fase Pertumbuhan Tomat,” Jurnal Teknik Informatika Unika ST. Thomas (JTIUST), vol. 10, no. 1, pp. 60–67, 2025.
[4] R. A. Safitri and E. Suhartono, “The Effect of Harvest Area, Rice Productivity, and Population Density on Food Security in NTT Province 2018–2023,” Jambura Equilibrium Journal, vol. 7, no. 2, pp. 71–78, 2025, doi: 10.37479.
[5] Ratnasari and D. Feriyanto, “Deteksi Penyakit Daun Padi Menggunakan Deep Learning untuk Mendukung Produktivitas dan Pertanian Berkelanjutan,” Jurnal Algoritma, vol. 22, no. 2, pp. 716–727, 2025, doi: 10.33364/algoritma/v.22-2.2900.
[6] B. W. Sari, D. Prabowo, Y. Pristyanto, and A. Aminuddin, “Transfer Learning-Based Convolutional Neural Network for Accurate Detection of Rice Leaf Disease in Precision Agriculture,” Journal of Information Systems Engineering and Business Intelligence, vol. 11, no. 3, pp. 420–432, 2025, doi: 10.20473/jisebi.11.3.420-432.
[7] M. E. Rana, V. A. Hameed, I. K. Y. Eng, H. K. Tripathy, and S. Mallik, “Harnessing Artificial Intelligence for Sustainable Rice Leaf Disease Classification,” Front. Plant Sci., vol. 16, pp. 1–27, 2025, doi: 10.3389/fpls.2025.1594329.
[8] P. Novantara, R. L. Firmansyah, and M. Arismawati, “Deteksi Hama Penyakit Daun Padi Dengan Menggunakan Teknik Optimasi Deep Learning Convolutional Neural Network,” bit-Tech, vol. 7, no. 3, pp. 975–983, 2025, doi: 10.32877/bt.v7i3.2284.
[9] D. Lizard, S. Dimara, B. Rahmat, and H. Maulana, “Identifikasi Penyakit Daun Padi dengan Metode Transfer Learning MobileNet–Support Vector Machine,” 2025.
[10] R. Suciani, D. A. Anugra, and E. Faisal, “Deteksi Penyakit Daun Padi Menggunakan Deep Learning dengan Arsitektur CNN,” Journal of Information Technology and Computer Science (INTECOMS), vol. 8, no. 5, pp. 1451–1463, 2025, doi: 10.23960/jitc.v8i5.1451.
[11] B. N. Kumar and S. Sakthivel, “Rice Leaf Disease Classification Using a Fusion Vision Approach,” Sci. Rep., vol. 15, no. 1, 2025, doi: 10.1038/s41598-025-87800-3.
[12] N. Istiqomah and M. Murinto, “Klasifikasi Penyakit Tanaman Padi Berbasis Citra Daun Menggunakan Convolutional Neural Network (CNN),” JSTIE (Jurnal Sarjana Teknik Informatika), vol. 12, no. 1, p. 18, 2024, doi: 10.12928/jstie.v12i1.27314.
[13] D. A. Pangestu, O. Q. Aziz, and C. Crysdian, “Klasifikasi Penyakit pada Tanaman Berdasarkan Citra Daun Menggunakan Metode Convolutional Neural Network,” JISKA (Jurnal Informatika Sunan Kalijaga), vol. 10, no. 2, pp. 235–248, 2025.
[14] R. Gunawan, F. Salim, A. I. Wahyudhy, A. Y. Wibowo, G. Yordan, and R. F. Filamori, “Klasifikasi Penyakit Daun Kentang dengan Transfer Learning Menggunakan CNN Optimalisasi Arsitektur MobileNetV2,” COSCITECH, vol. 6, no. 2, pp. 254–258, 2025, doi: 10.37859/coscitech.v6i2.8599.
[15] D. P. Pamungkas and M. F. Amrulloh, “Analisis Hasil Klasifikasi Penyakit Daun Bawang Merah Menggunakan CNN Arsitektur Exception,” JIPI (Jurnal Ilmiah Penelitian dan Pembelajaran Informatika), vol. 10, no. 1, pp. 359–366, 2025, doi: 10.29100/jipi.v10i1.5875.
[16] thntrngtnh, “Data Rice Leaf FN,” 2020. [Online]. Available: https://www.kaggle.com/datasets/thntrngtnh/data-rice-leaf-fn
[17] G. Gunawan, S. A. Wibowo, and W. Andriani, “Evaluasi Model Deep Learning pada Pola Dataset Biomedis,” Jurnal Saintekom: Sains, Teknologi, Komputer dan Manajemen, vol. 14, no. 2, pp. 195–207, 2024, doi: 10.33020/saintekom.v14i2.738.
[18] F. S. Maulana, V. S. Kusuma, W. M. Baihaqi, and P. Subarkah, “Optimasi Klasifikasi Gaya Belajar Mahasiswa Inklusif Berdasarkan Model VAK dengan Stratified Split dan Multilayer Perceptron,” Jurnal Teknologi Informasi dan Ilmu Komputer, vol. 12, no. 5, pp. 1163–1172, 2025.
[19] M. Purba, V. Ayumi, S. Rahayu, U. Salamah, I. Handriani, and I. Farida, “Penerapan Metode Random Contrast dan Brightness Range Pada Dataset Citra Daun Fitomedisin,” JSAI: Journal Scientific and Applied Informatics, vol. 8, no. 2, pp. 582–587, 2025, doi: 10.36085/jsai.v8i2.582.
[20] M. Ilham, S. Ernawati, and M. Indra, “Improving Image Classification Accuracy with Oversampling and Data Augmentation Using Deep Learning,” Jurnal Riset Informatika, vol. 6, no. 4, pp. 201–209, 2024, doi: 10.34288/jri.v6i4.348.
[21] M. Rijal, A. M. Yani, and A. Rahman, “Deteksi Citra Daun untuk Klasifikasi Penyakit Padi Menggunakan Pendekatan Deep Learning dengan Model CNN,” Jurnal Teknologi Terpadu, vol. 10, no. 1, pp. 56–62, 2024.
[22] R. Kusumastuti, T. D. Putra, and Z. Z. Yudam, “Klasifikasi Citra Penyakit Daun Jagung Menggunakan Algoritma CNN EfficientNet,” Multitek Indonesia Jurnal Ilmiah, vol. 17, no. 2, pp. 143–153, 2023.
[23] K. Prasetyo and R. Mahenra, “Performance Analysis of Baseline Convolutional Neural Networks for Identifying Potato Disease Types,” MALCOM: Indonesian Journal of Machine Learning and Computer Science, vol. 5, no. 2, pp. 609–615, Apr. 2025, doi: 10.57152/malcom.v5i2.1722.
[24] A. N. Zulfa, J. Jasril, M. Irsyad, F. Yanto, and S. Sanjaya, “Optimasi Convolutional Neural Network NASNetLarge Menggunakan Augmentasi Data untuk Klasifikasi Citra Penyakit Daun Padi,” Jurnal Media Informatika Budidarma, vol. 7, no. 2, pp. 696–706, Apr. 2023, doi: 10.30865/mib.v7i2.6056.
[25] A. Bahtiar, M. I. P. Hutomo, A. Widiyanto, and S. Khomsah, “Class Weighting Approach for Handling Imbalanced Data on Forest Fire Classification Using Efficient-Net-B1,” Jurnal Informatika Sunan Kalijaga (JISKA), vol. 10, no. 1, pp. 63–73, Jan. 2025, doi: 10.25181/jiska.v10i1.2987.
[26] Sariah, N. Suarna, I. Ali, and D. Solihudin, “Penerapan Convolutional Neural Network (CNN) untuk Prediksi Penyakit Tanaman Padi melalui Citra Daun,” Jurnal Komtika (Komputasi dan Informatika), vol. 9, no. 1, 2025, doi: 10.31603/komtika.v9i1.12852.
[27] H. P. Arianda and T. Y. Hadiwandra, “Implementation of Deep Learning for Disease Classification in Oil Palm Leaves Using the MobileNetV2 Architecture,” Jurnal Computer Science and Information Technology (CoSciTech), vol. 6, no. 3, pp. 453–462, 2025, doi: 10.37859/coscitech.v6i3.10306.
[28] O. V Putra, M. Z. Mustaqim, and D. Muriatmoko, “Transfer Learning untuk Klasifikasi Penyakit dan Hama Padi Menggunakan MobileNetV2,” Techno.COM, vol. 22, no. 3, pp. 562–575, 2023, doi: 10.33508/techno.v22i3.562-575.
[29] T. B. Sasongko, Haryoko, and A. Amrullah, “Analisis Efek Augmentasi Dataset dan Fine-Tune pada Algoritma Pre-Trained Convolutional Neural Network (CNN),” Jurnal Teknologi Informasi dan Ilmu Komputer (JTIIK), vol. 10, no. 4, pp. 763–768, 2023, doi: 10.25126/jtiik.2023106583.
[30] S. Ghosal and K. Sarkar, “Rice Leaf Diseases Classification Using CNN With Transfer Learning,” in 2020 IEEE Calcutta Conference (CALCON), IEEE, 2020. doi: 10.1109/CALCON49167.2020.9106423.
[31] I. Sahputra, A. F. Ulva, B. A. Putri, and C. Y. Eviyan, “Comparative Study of VGG16 and MobileNet Architectures for Rice Leaf Disease Classification Using CNN,” Journal of Informatics and Telecommunication Engineering, 2025.
[32] Md. S. I. Sobuj, Md. I. Hossen, and Md. F. Mahmud, “Leveraging Pre-trained CNNs for Efficient Feature Extraction in Rice Leaf Disease Classification,” arXiv preprint, 2024.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Muhammad Bisri Mustofa, Muhammad Arifin, Shofiatuz Zulfia
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License (Attribution-ShareAlike 4.0 International (CC BY-SA 4.0) ) that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
