Peningkatan Akurasi MobileNetV2 untuk Klasifikasi Penyakit Daun Jagung Berbasis Morfologi
DOI:
https://doi.org/10.35968/jsi.v13i1.1733Kata Kunci:
deep learning_ morfologi citra_ MobileNetV2_ penyakit daun jagung_ transfer learningAbstrak
Deteksi penyakit daun jagung pada citra lapangan menghadapi tantangan besar akibat pencahayaan tidak merata, latar belakang kompleks, serta jumlah data yang terbatas dan tidak seimbang. Penelitian ini mengusulkan pipeline klasifikasi berbasis deep learning yang mengintegrasikan pra-pemrosesan morfologi erosi, dilasi, opening, dan closing—untuk memperjelas struktur lesi sebelum pelatihan model. Sebanyak 310 citra daun jagung dalam tiga kelas (Sehat, Karat, dan Hawar) dibagi secara stratifikasi menjadi data latih, validasi, dan uji. MobileNetV2 dilatih menggunakan pendekatan transfer learning dengan augmentasi dasar. Hasil evaluasi menunjukkan akurasi validasi 34,43%, akurasi uji 44,83%, dan macro-F1 sebesar 0,17, yang mengindikasikan kemampuan generalisasi rendah. Confusion matrix mengungkap terjadinya class collapse akibat ketidakseimbangan kelas dan kemiripan visual antar penyakit. Meskipun performanya terbatas, pra-pemrosesan morfologi membantu meningkatkan kejelasan fitur dan stabilitas ekstraksi pada kondisi lapangan.Referensi
Abade, A., Ferreira, P. A., & Vidal, F. de B. (2021). Plant diseases recognition on images using convolutional neural networks: A systematic review. Computers and Electronics in …. https://www.sciencedirect.com/science/article/pii/S0168169921001435
Adegun, A. A., Viriri, S., & Tapamo, J.-R. (2023). Review of deep learning methods for remote sensing satellite images classification: experimental survey and comparative analysis. Journal of Big Data, 10, Article 93. https://doi.org/10.1186/s40537-023-00772-x
Awaludin, M. (2015). Penerapan Metode Distance Transform Pada Linear Discriminant Analysis Untuk Kemunculan Kulit Pada Deteksi Kulit. Journal of Intelligent Systems, 1(1), 49–55.
Awaludin, M., Nuryadi, H., & Pribadi, G. N. (2024). Sistem Otomatisasi Laporan untuk Optimalisasi Pelaporan Data Penelitian dan Pengabdian kepada Masyarakat di Universitas Dirgantara Marsekal Suryadarma. 9675, 1–7.
Awaludin, M., & Yasin, V. (2020). Application Of Oriented Fast And Rotated Brief ( Orb ) And Bruteforce Hamming In Library Opencv For Classification. Journal of Information System, Applied, Managemgent, Accounting, and Reserarch, 4(3), 51–59.
Chitraningrum, N., Banowati, L., Herdiana, D., & Mulyati, B. (2024). Comparison Study of Corn Leaf Disease Detection based on Deep Learning YOLO-v5 and YOLO-v8. Journal of Engineering and Technological Sciences, 56(1), 61–70. https://doi.org/10.5614/j.eng.technol.sci.2024.56.1.5
Demilie, W. B., & Wubetu, D. (2024). Revolutionizing crop disease detection with computational deep learning: A comprehensive review. Environmental Monitoring and Assessment, 196, 302. https://doi.org/10.1007/s10661-024-12454-z
Fadhilla, M., Suryani, D., Labellapansa, A., & ... (2023). Corn leaf diseases recognition based on convolutional neural network. IT Journal Research …. https://repository.uir.ac.id/22407/
Gulzar, Y. (2023). Fruit Image Classification Model Based on MobileNetV2 with Deep Transfer Learning Technique. Sustainability, 15(3), 1906. https://doi.org/10.3390/su15031906
Joseph, N. (2025). A Review on Automated Plant Disease Detection: Motivation, Limitations, Challenges, and Recent Advancements for Future Research. Journal of King Saud University - Computer and Information Sciences.
Kaur, K., & Bansal, K. (2024). Enhancing Plant Disease Detection Using Advanced Deep Learning Models. Indian Journal of Science and Technology, 17(17), 1755–1766.
Lamba, S., Kukreja, V., Rashid, J., Gadekallu, T. R., Kim, J., Baliyan, A., & Saini, S. (2023). A novel fine-tuned deep-learning-based multi-class classifier for severity of paddy leaf diseases. Frontiers in Plant Science, 14. https://doi.org/10.3389/fpls.2023.1234067
Mohanty, P., & al., et. (2023). [Judul artikel tidak disebutkan]. CSXAI.
Ojo, M. O., & Zahid, A. (2023). Improving Deep Learning Classifiers Performance via Preprocessing and Class Imbalance Approaches in a Plant Disease Detection Pipeline. Agronomy, 13(3), 887. https://doi.org/10.3390/agronomy13030887
Özüpak, Y., Alpsalaz, F., Aslan, E., & ... (2025). Hybrid deep learning model for maize leaf disease classification with explainable AI. New Zealand Journal of …. https://doi.org/10.1080/01140671.2025.2519570
Qian, X., Zhang, C., Chen, L., & Li, K. (2022). Deep learning-based identification of maize leaf diseases is improved by an attention mechanism: Self-attention. Frontiers in Plant Science, 13, 864486. https://doi.org/10.3389/fpls.2022.864486
Shoaib, M., Shah, B., El-Sappagh, S., Ali, A., Ullah, A., Alenezi, F., Gechev, T., & Hussain, T. (2023). An advanced deep learning models-based plant disease detection: A review of recent research. Frontiers in Plant Science, 14, Article 1158933. https://doi.org/10.3389/fpls.2023.1158933
Wang, L., & Liu, J. (2024). [Unspecified title]. [Unspecified Journal].
Zhou, H., Chen, J., Niu, X., Dai, Z., Qin, L., Ma, L., Li, J., & ... (2024). Identification of leaf diseases in field crops based on improved ShuffleNetV2. In Frontiers in Plant …. frontiersin.org. https://doi.org/10.3389/fpls.2024.1342123
